{"task":"Graph Classification","dataset":"MUTAG","metric_names":["Accuracy","Accuracy (10-fold)","Mean Accuracy","Accuracy (10 fold)"],"rows":[{"id":95444,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Evolution of Graph Classifiers","metrics":{"Accuracy":"100.00%","Accuracy (10-fold)":"100"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/8923110","paper_title":"Evolution of Graph Classifiers","paper_date":"2019-10-04","code_links":[{"title":"rohand24/GraphCNN_evolution","url":"https://github.com/rohand24/GraphCNN_evolution"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95445,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"MEWISPool","metrics":{"Accuracy":"96.66%"},"paper_url":"https://arxiv.org/abs/2107.01410v1","paper_title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","paper_date":"2021-07-03","code_links":[{"title":"mewispool/mewispool","url":"https://github.com/mewispool/mewispool"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95446,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"TFGW ADJ (L=2)","metrics":{"Accuracy":"96.4%"},"paper_url":"https://arxiv.org/abs/2205.15733v1","paper_title":"Template based Graph Neural Network with Optimal Transport Distances","paper_date":"2022-05-31","code_links":[{"title":"cedricvincentcuaz/TFGW","url":"https://github.com/cedricvincentcuaz/TFGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95447,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GIUNet","metrics":{"Accuracy":"95.7%"},"paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0957417423017827#preview-section-abstract","paper_title":"Graph isomorphism UNet","paper_date":"2023-08-23","code_links":[{"title":"aramiracle/GIUNet","url":"https://github.com/aramiracle/GIUNet"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95448,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"G_Inception","metrics":{"Accuracy":"95.00%"},"paper_url":"http://arxiv.org/abs/1807.02653v1","paper_title":"When Work Matters: Transforming Classical Network Structures to Graph CNN","paper_date":"2018-07-07","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95449,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GIC","metrics":{"Accuracy":"94.44%"},"paper_url":"http://arxiv.org/abs/1811.04393v1","paper_title":"Gaussian-Induced Convolution for Graphs","paper_date":"2018-11-11","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95450,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"CIN++","metrics":{"Accuracy":"94.4%"},"paper_url":"https://arxiv.org/abs/2306.03561v1","paper_title":"CIN++: Enhancing Topological Message Passing","paper_date":"2023-06-06","code_links":[{"title":"twitter-research/cwn","url":"https://github.com/twitter-research/cwn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95451,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"sGIN","metrics":{"Accuracy":"94.14%"},"paper_url":"https://arxiv.org/abs/1905.08509v4","paper_title":"Mutual Information Maximization in Graph Neural Networks","paper_date":"2019-05-21","code_links":[{"title":"CODE-SUBMIT/Graph_Neighborhood_1","url":"https://github.com/CODE-SUBMIT/Graph_Neighborhood_1"},{"title":"CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network","url":"https://github.com/CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":95452,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"CAN","metrics":{"Accuracy":"94.1%"},"paper_url":"https://arxiv.org/abs/2209.08179v1","paper_title":"Cell Attention Networks","paper_date":"2022-09-16","code_links":[{"title":"lrnzgiusti/can","url":"https://github.com/lrnzgiusti/can"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95453,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Deep WL SGN(0,1,2)","metrics":{"Accuracy":"93.68%"},"paper_url":"https://arxiv.org/abs/1903.09022v3","paper_title":"Subgraph Networks with Application to Structural Feature Space Expansion","paper_date":"2019-03-21","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95454,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"QS-CNNs (Quantum Walk)","metrics":{"Accuracy":"93.13%","Accuracy (10-fold)":"93.13"},"paper_url":"https://doi.org/10.1016/j.patcog.2018.11.002","paper_title":"Quantum-based subgraph convolutional neural networks","paper_date":"2019-04-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95455,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"PATCHY-SAN","metrics":{"Accuracy":"92.63%"},"paper_url":"http://arxiv.org/abs/1605.05273v4","paper_title":"Learning Convolutional Neural Networks for Graphs","paper_date":"2016-05-17","code_links":[{"title":"tvayer/PSCN","url":"https://github.com/tvayer/PSCN"},{"title":"CielAl/PatchySan","url":"https://github.com/CielAl/PatchySan"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95456,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"DDGK","metrics":{"Accuracy":"91.58%"},"paper_url":"http://arxiv.org/abs/1904.09671v1","paper_title":"DDGK: Learning Graph Representations for Deep Divergence Graph Kernels","paper_date":"2019-04-21","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/graph_embedding/ddgk"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95457,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Graph-JEPA","metrics":{"Accuracy":"91.25%"},"paper_url":"https://arxiv.org/abs/2309.16014v3","paper_title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","paper_date":"2023-09-27","code_links":[{"title":"geriskenderi/graph-jepa","url":"https://github.com/geriskenderi/graph-jepa"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95458,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GraphStar","metrics":{"Accuracy":"91.2%"},"paper_url":"https://arxiv.org/abs/1906.12330v1","paper_title":"Graph Star Net for Generalized Multi-Task Learning","paper_date":"2019-06-21","code_links":[{"title":"graph-star-team/graph_star","url":"https://github.com/graph-star-team/graph_star"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95459,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"TREE-G","metrics":{"Accuracy":"91.1%"},"paper_url":"https://arxiv.org/abs/2207.02760v5","paper_title":"TREE-G: Decision Trees Contesting Graph Neural Networks","paper_date":"2022-07-06","code_links":[{"title":"mayabechlerspeicher/tree-g","url":"https://github.com/mayabechlerspeicher/tree-g"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95460,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"SEG-BERT","metrics":{"Accuracy":"90.85%"},"paper_url":"https://arxiv.org/abs/2002.03283v1","paper_title":"Segmented Graph-Bert for Graph Instance Modeling","paper_date":"2020-02-09","code_links":[{"title":"jwzhanggy/SEG-BERT","url":"https://github.com/jwzhanggy/SEG-BERT"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95461,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GFN","metrics":{"Accuracy":"90.84%"},"paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","paper_date":"2019-05-11","code_links":[{"title":"chentingpc/gfn","url":"https://github.com/chentingpc/gfn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95462,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"PPGN","metrics":{"Accuracy":"90.55%"},"paper_url":"https://arxiv.org/abs/1905.11136v4","paper_title":"Provably Powerful Graph Networks","paper_date":"2019-05-27","code_links":[{"title":"hadarser/ProvablyPowerfulGraphNetworks_torch","url":"https://github.com/hadarser/ProvablyPowerfulGraphNetworks_torch"},{"title":"hadarser/ProvablyPowerfulGraphNetworks","url":"https://github.com/hadarser/ProvablyPowerfulGraphNetworks"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95463,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GAT-GC (f-Scaled)","metrics":{"Accuracy":"90.44%"},"paper_url":"https://arxiv.org/abs/1907.02204v4","paper_title":"Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation","paper_date":"2019-07-04","code_links":[{"title":"zetayue/CPA","url":"https://github.com/zetayue/CPA"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":95464,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"DropGIN","metrics":{"Accuracy":"90.4%"},"paper_url":"https://arxiv.org/abs/2111.06283v1","paper_title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","paper_date":"2021-11-11","code_links":[{"title":"karolismart/dropgnn","url":"https://github.com/karolismart/dropgnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95465,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"LDP","metrics":{"Accuracy":"90.1%"},"paper_url":"https://arxiv.org/abs/1811.03508v3","paper_title":"A simple yet effective baseline for non-attributed graph classification","paper_date":"2018-11-08","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"Chen-Cai-OSU/LDP","url":"https://github.com/Chen-Cai-OSU/LDP"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95466,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"R-GCN + PANDA","metrics":{"Accuracy":"90.05%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95467,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"hGANet","metrics":{"Accuracy":"90.00%"},"paper_url":"https://arxiv.org/abs/1907.04652v1","paper_title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","paper_date":"2019-07-05","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hardgat"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95468,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"U2GNN","metrics":{"Accuracy":"89.97%"},"paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","paper_date":"2019-09-26","code_links":[{"title":"daiquocnguyen/Graph-Transformer","url":"https://github.com/daiquocnguyen/Graph-Transformer"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95469,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"FactorGCN","metrics":{"Accuracy":"89.9%","Accuracy (10-fold)":"89.9%"},"paper_url":"https://arxiv.org/abs/2010.05421v1","paper_title":"Factorizable Graph Convolutional Networks","paper_date":"2020-10-12","code_links":[{"title":"ihollywhy/FactorGCN.PyTorch","url":"https://github.com/ihollywhy/FactorGCN.PyTorch"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95470,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GFN-light","metrics":{"Accuracy":"89.89%"},"paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","paper_date":"2019-05-11","code_links":[{"title":"chentingpc/gfn","url":"https://github.com/chentingpc/gfn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95471,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GIN-0","metrics":{"Accuracy":"89.4%"},"paper_url":"http://arxiv.org/abs/1810.00826v3","paper_title":"How Powerful are Graph Neural Networks?","paper_date":"2018-10-01","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gin"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/gin"},{"title":"weihua916/powerful-gnns","url":"https://github.com/weihua916/powerful-gnns"},{"title":"lukecavabarrett/pna","url":"https://github.com/lukecavabarrett/pna"},{"title":"gospodima/extended-simgnn","url":"https://github.com/gospodima/extended-simgnn"},{"title":"calciver/Graph-Isomorphism-Networks","url":"https://github.com/calciver/Graph-Isomorphism-Networks"},{"title":"yuwvandy/g2gnn","url":"https://github.com/yuwvandy/g2gnn"},{"title":"PurdueMINDS/RelationalPooling","url":"https://github.com/PurdueMINDS/RelationalPooling"},{"title":"alexOarga/haiku-geometric","url":"https://github.com/alexOarga/haiku-geometric/blob/main/haiku_geometric/nn/conv/gin_conv.py"},{"title":"karolismart/dropgnn","url":"https://github.com/karolismart/dropgnn"},{"title":"egyptdj/graph-neural-mapping","url":"https://github.com/egyptdj/graph-neural-mapping"},{"title":"guillaumejaume/tuto-dl-on-graphs","url":"https://github.com/guillaumejaume/tuto-dl-on-graphs"},{"title":"pfnet-research/treewidth-prediction","url":"https://github.com/pfnet-research/treewidth-prediction"},{"title":"gmum/umwpl2021","url":"https://github.com/gmum/umwpl2021"},{"title":"zhliping/Deep-Learning","url":"https://github.com/zhliping/Deep-Learning"},{"title":"k4my4r/ECG-Classification","url":"https://github.com/k4my4r/ECG-Classification"},{"title":"igorsterner/commute-opt-gnn","url":"https://github.com/igorsterner/commute-opt-gnn"},{"title":"mfmceneaney/Lambda-GNNs","url":"https://github.com/mfmceneaney/Lambda-GNNs"},{"title":"willy-b/tiny-GIN-for-ogbg-molhiv","url":"https://github.com/willy-b/tiny-GIN-for-ogbg-molhiv"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":95472,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Multigraph ChebNet","metrics":{"Accuracy":"89.1%"},"paper_url":"http://arxiv.org/abs/1811.09595v1","paper_title":"Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules","paper_date":"2018-11-23","code_links":[{"title":"bknyaz/graph_nn","url":"https://github.com/bknyaz/graph_nn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95473,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"InfoGraph","metrics":{"Accuracy":"89.01%"},"paper_url":"https://arxiv.org/abs/1908.01000v3","paper_title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","paper_date":"2019-07-31","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/infograph"},{"title":"fanyun-sun/InfoGraph","url":"https://github.com/fanyun-sun/InfoGraph"},{"title":"yuwvandy/g2gnn","url":"https://github.com/yuwvandy/g2gnn"},{"title":"hengruizhang98/InfoGraph","url":"https://github.com/hengruizhang98/InfoGraph"},{"title":"ycremar/DIG-SSL","url":"https://github.com/ycremar/DIG-SSL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95474,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"PSCN","metrics":{"Accuracy":"88.95%"},"paper_url":"http://arxiv.org/abs/1605.05273v4","paper_title":"Learning Convolutional Neural Networks for Graphs","paper_date":"2016-05-17","code_links":[{"title":"tvayer/PSCN","url":"https://github.com/tvayer/PSCN"},{"title":"CielAl/PatchySan","url":"https://github.com/CielAl/PatchySan"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95475,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"BC + Capsules","metrics":{"Accuracy":"88.9%"},"paper_url":"http://arxiv.org/abs/1902.08399v1","paper_title":"Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations","paper_date":"2019-02-22","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95476,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"edGNN (max)","metrics":{"Accuracy":"88.8%"},"paper_url":"https://arxiv.org/abs/1904.08745v2","paper_title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","paper_date":"2019-04-18","code_links":[{"title":"guillaumejaume/edGNN","url":"https://github.com/guillaumejaume/edGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95477,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GIN + PANDA","metrics":{"Accuracy":"88.75%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95478,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"NERO","metrics":{"Accuracy":"88.68%"},"paper_url":"https://link.springer.com/chapter/10.1007/978-3-030-77964-1_18","paper_title":"Relation order histograms as a network embedding tool","paper_date":"2021-06-09","code_links":[{"title":"Prpht/NERO","url":"https://github.com/Prpht/NERO"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95479,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Path up to length h","metrics":{"Accuracy":"88.47%"},"paper_url":"https://hal-normandie-univ.archives-ouvertes.fr/hal-02053946/","paper_title":"Graph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons","paper_date":"2019-03-01","code_links":[{"title":"jajupmochi/graphkit-learn","url":"https://github.com/jajupmochi/graphkit-learn"},{"title":"jajupmochi/py-graph","url":"https://github.com/jajupmochi/py-graph"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95480,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"U2GNN (Unsupervised)","metrics":{"Accuracy":"88.47%"},"paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","paper_date":"2019-09-26","code_links":[{"title":"daiquocnguyen/Graph-Transformer","url":"https://github.com/daiquocnguyen/Graph-Transformer"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95481,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"FGW wl h=4 sp","metrics":{"Accuracy":"88.42%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95482,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"SF + RFC","metrics":{"Accuracy":"88.4%"},"paper_url":"http://arxiv.org/abs/1810.09155v2","paper_title":"A Simple Baseline Algorithm for Graph Classification","paper_date":"2018-10-22","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"edouardpineau/A-simple-baseline-algorithm-for-graph-classification","url":"https://github.com/edouardpineau/A-simple-baseline-algorithm-for-graph-classification"},{"title":"edouardpineau/Using-Laplacian-Spectrum-as-Graph-Feature-Representation","url":"https://github.com/edouardpineau/Using-Laplacian-Spectrum-as-Graph-Feature-Representation"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95483,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"ECC (5 scores)","metrics":{"Accuracy":"88.33%"},"paper_url":"http://arxiv.org/abs/1704.02901v3","paper_title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","paper_date":"2017-04-10","code_links":[{"title":"rusty1s/pytorch_cluster","url":"https://github.com/rusty1s/pytorch_cluster"},{"title":"mys007/ecc","url":"https://github.com/mys007/ecc"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95484,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"WEGL","metrics":{"Accuracy":"88.3%"},"paper_url":"https://arxiv.org/abs/2006.09430v2","paper_title":"Wasserstein Embedding for Graph Learning","paper_date":"2020-06-16","code_links":[{"title":"navid-naderi/WEGL","url":"https://github.com/navid-naderi/WEGL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95485,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"R-GIN + PANDA","metrics":{"Accuracy":"88.2%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95486,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"AWE","metrics":{"Accuracy":"87.87%"},"paper_url":"http://arxiv.org/abs/1805.11921v3","paper_title":"Anonymous Walk Embeddings","paper_date":"2018-05-30","code_links":[{"title":"nd7141/AWE","url":"https://github.com/nd7141/AWE"},{"title":"paulmorio/geo2dr","url":"https://github.com/paulmorio/geo2dr"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95487,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Graphlet Kernel","metrics":{"Accuracy":"87.7%"},"paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","paper_date":"2018-10-04","code_links":[{"title":"chrsmrrs/k-gnn","url":"https://github.com/chrsmrrs/k-gnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95488,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"CT-Layer","metrics":{"Accuracy":"87.58%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95489,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"WKPI-kcenters","metrics":{"Accuracy":"87.5%"},"paper_url":"https://arxiv.org/abs/1904.12189v2","paper_title":"Learning metrics for persistence-based summaries and applications for graph classification","paper_date":"2019-04-27","code_links":[{"title":"topology474/WKPI","url":"https://github.com/topology474/WKPI"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95490,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"DGK","metrics":{"Accuracy":"87.44%"},"paper_url":"https://www.semanticscholar.org/paper/Deep-Graph-Kernels-Yanardag-Vishwanathan/8ccd0adb1a00358ede79f1d9bdcce472dc1cb8d4","paper_title":"Deep Graph Kernels","paper_date":"2015-08-10","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95491,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"WWL","metrics":{"Accuracy":"87.27%"},"paper_url":"https://arxiv.org/abs/1906.01277v2","paper_title":"Wasserstein Weisfeiler-Lehman Graph Kernels","paper_date":"2019-06-04","code_links":[{"title":"BorgwardtLab/WWL","url":"https://github.com/BorgwardtLab/WWL"},{"title":"wenbintum/wwl-gpr","url":"https://github.com/wenbintum/wwl-gpr"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95492,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"DAGCN","metrics":{"Accuracy":"87.22%"},"paper_url":"http://arxiv.org/abs/1904.02278v1","paper_title":"DAGCN: Dual Attention Graph Convolutional Networks","paper_date":"2019-04-04","code_links":[{"title":"dawenzi123/DAGCN","url":"https://github.com/dawenzi123/DAGCN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95493,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GDL-g (SP)","metrics":{"Accuracy":"87.09%"},"paper_url":"https://arxiv.org/abs/2102.06555v2","paper_title":"Online Graph Dictionary Learning","paper_date":"2021-02-12","code_links":[{"title":"cedricvincentcuaz/GDL","url":"https://github.com/cedricvincentcuaz/GDL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95494,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"edGNN (avg)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/1904.08745v2","paper_title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","paper_date":"2019-04-18","code_links":[{"title":"guillaumejaume/edGNN","url":"https://github.com/guillaumejaume/edGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95495,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GAP-Layer (Rcut)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95496,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GAP-Layer (Ncut)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95497,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"CapsGNN","metrics":{"Accuracy":"86.67%"},"paper_url":"https://openreview.net/forum?id=Byl8BnRcYm","paper_title":"Capsule Graph Neural Network","paper_date":"2019-05-01","code_links":[{"title":"benedekrozemberczki/CapsGNN","url":"https://github.com/benedekrozemberczki/CapsGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95498,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"FGW wl h=2 sp","metrics":{"Accuracy":"86.42%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95499,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"ApproxRepSet","metrics":{"Accuracy":"86.33%"},"paper_url":"https://arxiv.org/abs/1904.01962v2","paper_title":"Rep the Set: Neural Networks for Learning Set Representations","paper_date":"2019-04-03","code_links":[{"title":"giannisnik/repset","url":"https://github.com/giannisnik/repset"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95500,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"VRGC","metrics":{"Accuracy":"86.3%"},"paper_url":"https://arxiv.org/abs/1902.02721v4","paper_title":"Variational Recurrent Neural Networks for Graph Classification","paper_date":"2019-02-07","code_links":[{"title":"edouardpineau/Variational-Recurrent-Neural-Networks-for-Graph-Classification","url":"https://github.com/edouardpineau/Variational-Recurrent-Neural-Networks-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95501,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"k-GNN","metrics":{"Accuracy":"86.1%"},"paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","paper_date":"2018-10-04","code_links":[{"title":"chrsmrrs/k-gnn","url":"https://github.com/chrsmrrs/k-gnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95502,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"DGCNN","metrics":{"Accuracy":"85.83%"},"paper_url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","paper_title":"An End-to-End Deep Learning Architecture for Graph Classification","paper_date":"2018-04-29","code_links":[{"title":"muhanzhang/DGCNN","url":"https://github.com/muhanzhang/DGCNN"},{"title":"Ki-Seki/DGCNN-updated","url":"https://github.com/Ki-Seki/DGCNN-updated"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95503,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GCN + PANDA","metrics":{"Accuracy":"85.75%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":95504,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GIN-0","metrics":{"Accuracy":"85.7%"},"paper_url":"http://arxiv.org/abs/1903.02428v3","paper_title":"Fast Graph Representation Learning with PyTorch Geometric","paper_date":"2019-03-06","code_links":[{"title":"rusty1s/pytorch_geometric","url":"https://github.com/rusty1s/pytorch_geometric"},{"title":"leojklarner/gauche","url":"https://github.com/leojklarner/gauche"},{"title":"ncfrey/litmatter","url":"https://github.com/ncfrey/litmatter"},{"title":"long-9621/splinecnn","url":"https://github.com/long-9621/splinecnn"},{"title":"luxtu/OCTA-graph","url":"https://github.com/luxtu/OCTA-graph"},{"title":"NMADALI97/French-web-domain-classification","url":"https://github.com/NMADALI97/French-web-domain-classification"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":95505,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"NDP","metrics":{"Accuracy":"84.7%"},"paper_url":"https://arxiv.org/abs/1910.11436v3","paper_title":"Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling","paper_date":"2019-10-24","code_links":[{"title":"danielegrattarola/decimation-pooling","url":"https://github.com/danielegrattarola/decimation-pooling"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95506,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Propagation kernels (pk)","metrics":{"Accuracy":"84.5%"},"paper_url":"https://doi.org/10.1007/s10994-015-5517-9","paper_title":"Propagation kernels: efficient graph kernels from propagated information","paper_date":"2019-02-01","code_links":[{"title":"marionmari/propagation_kernels","url":"https://github.com/marionmari/propagation_kernels"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95507,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"WL-OA","metrics":{"Accuracy":"84.5%"},"paper_url":"http://arxiv.org/abs/1606.01141v3","paper_title":"On Valid Optimal Assignment Kernels and Applications to Graph Classification","paper_date":"2016-06-03","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95508,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"SPI-GCN","metrics":{"Accuracy":"84.40%"},"paper_url":"https://hal.archives-ouvertes.fr/hal-02093451/","paper_title":"SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network","paper_date":"2019-04-08","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95509,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GMT","metrics":{"Accuracy":"83.44%"},"paper_url":"https://arxiv.org/abs/2102.11533v4","paper_title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","paper_date":"2021-02-23","code_links":[{"title":"JinheonBaek/GMT","url":"https://github.com/JinheonBaek/GMT"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95510,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Function Space Pooling","metrics":{"Accuracy":"83.3%"},"paper_url":"https://arxiv.org/abs/1905.06259v2","paper_title":"Function Space Pooling For Graph Convolutional Networks","paper_date":"2019-05-15","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95511,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"Function Space Pooling","metrics":{"Accuracy":"83.3%"},"paper_url":"https://arxiv.org/abs/1907.09495v2","paper_title":"IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification","paper_date":"2019-07-22","code_links":[{"title":"linmengsysu/IsoNN","url":"https://github.com/linmengsysu/IsoNN"},{"title":"jwzhanggy/isocapsnet","url":"https://github.com/jwzhanggy/isocapsnet"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95512,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"FGW raw sp","metrics":{"Accuracy":"83.26%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95513,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"graph2vec","metrics":{"Accuracy":"83.15% ± 9.25%"},"paper_url":"http://arxiv.org/abs/1707.05005v1","paper_title":"graph2vec: Learning Distributed Representations of Graphs","paper_date":"2017-07-17","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"benedekrozemberczki/graph2vec","url":"https://github.com/benedekrozemberczki/graph2vec"},{"title":"MLDroid/graph2vec_tf","url":"https://github.com/MLDroid/graph2vec_tf"},{"title":"paulmorio/geo2dr","url":"https://github.com/paulmorio/geo2dr"},{"title":"compnet/pang","url":"https://github.com/compnet/pang"},{"title":"soumavaghosh/graph2vec","url":"https://github.com/soumavaghosh/graph2vec"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95514,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"EigenGCN-3","metrics":{"Accuracy":"79.5%"},"paper_url":"https://arxiv.org/abs/1904.13107v2","paper_title":"Graph Convolutional Networks with EigenPooling","paper_date":"2019-04-30","code_links":[{"title":"alge24/eigenpooling","url":"https://github.com/alge24/eigenpooling"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95515,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"GDL-g (ADJ)","metrics":{"Accuracy":"58.45%"},"paper_url":"https://arxiv.org/abs/2102.06555v2","paper_title":"Online Graph Dictionary Learning","paper_date":"2021-02-12","code_links":[{"title":"cedricvincentcuaz/GDL","url":"https://github.com/cedricvincentcuaz/GDL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95516,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"P-WL-C","metrics":{"Mean Accuracy":"90.51"},"paper_url":"http://proceedings.mlr.press/v97/rieck19a.html","paper_title":"A Persistent Weisfeiler–Lehman Procedure for Graph Classification","paper_date":"2019-06-09","code_links":[{"title":"BorgwardtLab/P-WL","url":"https://github.com/BorgwardtLab/P-WL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":95517,"task":"Graph Classification","parent_task":null,"dataset":"MUTAG","model_name":"G-Tuning","metrics":{"Accuracy (10 fold)":"86.14"},"paper_url":"https://arxiv.org/abs/2312.13583v1","paper_title":"Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns","paper_date":"2023-12-21","code_links":[{"title":"zjunet/G-Tuning","url":"https://github.com/zjunet/G-Tuning"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122213,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Evolution of Graph Classifiers","metrics":{"Accuracy":"100.00%","Accuracy (10-fold)":"100"},"paper_url":"https://ieeexplore.ieee.org/abstract/document/8923110","paper_title":"Evolution of Graph Classifiers","paper_date":"2019-10-04","code_links":[{"title":"rohand24/GraphCNN_evolution","url":"https://github.com/rohand24/GraphCNN_evolution"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122214,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"MEWISPool","metrics":{"Accuracy":"96.66%"},"paper_url":"https://arxiv.org/abs/2107.01410v1","paper_title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","paper_date":"2021-07-03","code_links":[{"title":"mewispool/mewispool","url":"https://github.com/mewispool/mewispool"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122215,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"TFGW ADJ (L=2)","metrics":{"Accuracy":"96.4%"},"paper_url":"https://arxiv.org/abs/2205.15733v1","paper_title":"Template based Graph Neural Network with Optimal Transport Distances","paper_date":"2022-05-31","code_links":[{"title":"cedricvincentcuaz/TFGW","url":"https://github.com/cedricvincentcuaz/TFGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122216,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GIUNet","metrics":{"Accuracy":"95.7%"},"paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0957417423017827#preview-section-abstract","paper_title":"Graph isomorphism UNet","paper_date":"2023-08-23","code_links":[{"title":"aramiracle/GIUNet","url":"https://github.com/aramiracle/GIUNet"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122217,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"G_Inception","metrics":{"Accuracy":"95.00%"},"paper_url":"http://arxiv.org/abs/1807.02653v1","paper_title":"When Work Matters: Transforming Classical Network Structures to Graph CNN","paper_date":"2018-07-07","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122218,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GIC","metrics":{"Accuracy":"94.44%"},"paper_url":"http://arxiv.org/abs/1811.04393v1","paper_title":"Gaussian-Induced Convolution for Graphs","paper_date":"2018-11-11","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122219,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"CIN++","metrics":{"Accuracy":"94.4%"},"paper_url":"https://arxiv.org/abs/2306.03561v1","paper_title":"CIN++: Enhancing Topological Message Passing","paper_date":"2023-06-06","code_links":[{"title":"twitter-research/cwn","url":"https://github.com/twitter-research/cwn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122220,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"sGIN","metrics":{"Accuracy":"94.14%"},"paper_url":"https://arxiv.org/abs/1905.08509v4","paper_title":"Mutual Information Maximization in Graph Neural Networks","paper_date":"2019-05-21","code_links":[{"title":"CODE-SUBMIT/Graph_Neighborhood_1","url":"https://github.com/CODE-SUBMIT/Graph_Neighborhood_1"},{"title":"CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network","url":"https://github.com/CODE-SUBMIT/Neighborhood-Enlargement-in-Graph-Network"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":122221,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"CAN","metrics":{"Accuracy":"94.1%"},"paper_url":"https://arxiv.org/abs/2209.08179v1","paper_title":"Cell Attention Networks","paper_date":"2022-09-16","code_links":[{"title":"lrnzgiusti/can","url":"https://github.com/lrnzgiusti/can"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122222,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Deep WL SGN(0,1,2)","metrics":{"Accuracy":"93.68%"},"paper_url":"https://arxiv.org/abs/1903.09022v3","paper_title":"Subgraph Networks with Application to Structural Feature Space Expansion","paper_date":"2019-03-21","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122223,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"QS-CNNs (Quantum Walk)","metrics":{"Accuracy":"93.13%","Accuracy (10-fold)":"93.13"},"paper_url":"https://doi.org/10.1016/j.patcog.2018.11.002","paper_title":"Quantum-based subgraph convolutional neural networks","paper_date":"2019-04-01","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122224,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"PATCHY-SAN","metrics":{"Accuracy":"92.63%"},"paper_url":"http://arxiv.org/abs/1605.05273v4","paper_title":"Learning Convolutional Neural Networks for Graphs","paper_date":"2016-05-17","code_links":[{"title":"tvayer/PSCN","url":"https://github.com/tvayer/PSCN"},{"title":"CielAl/PatchySan","url":"https://github.com/CielAl/PatchySan"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122225,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"DDGK","metrics":{"Accuracy":"91.58%"},"paper_url":"http://arxiv.org/abs/1904.09671v1","paper_title":"DDGK: Learning Graph Representations for Deep Divergence Graph Kernels","paper_date":"2019-04-21","code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/graph_embedding/ddgk"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122226,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Graph-JEPA","metrics":{"Accuracy":"91.25%"},"paper_url":"https://arxiv.org/abs/2309.16014v3","paper_title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","paper_date":"2023-09-27","code_links":[{"title":"geriskenderi/graph-jepa","url":"https://github.com/geriskenderi/graph-jepa"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122227,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GraphStar","metrics":{"Accuracy":"91.2%"},"paper_url":"https://arxiv.org/abs/1906.12330v1","paper_title":"Graph Star Net for Generalized Multi-Task Learning","paper_date":"2019-06-21","code_links":[{"title":"graph-star-team/graph_star","url":"https://github.com/graph-star-team/graph_star"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122228,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"TREE-G","metrics":{"Accuracy":"91.1%"},"paper_url":"https://arxiv.org/abs/2207.02760v5","paper_title":"TREE-G: Decision Trees Contesting Graph Neural Networks","paper_date":"2022-07-06","code_links":[{"title":"mayabechlerspeicher/tree-g","url":"https://github.com/mayabechlerspeicher/tree-g"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122229,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"SEG-BERT","metrics":{"Accuracy":"90.85%"},"paper_url":"https://arxiv.org/abs/2002.03283v1","paper_title":"Segmented Graph-Bert for Graph Instance Modeling","paper_date":"2020-02-09","code_links":[{"title":"jwzhanggy/SEG-BERT","url":"https://github.com/jwzhanggy/SEG-BERT"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122230,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GFN","metrics":{"Accuracy":"90.84%"},"paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","paper_date":"2019-05-11","code_links":[{"title":"chentingpc/gfn","url":"https://github.com/chentingpc/gfn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122231,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"PPGN","metrics":{"Accuracy":"90.55%"},"paper_url":"https://arxiv.org/abs/1905.11136v4","paper_title":"Provably Powerful Graph Networks","paper_date":"2019-05-27","code_links":[{"title":"hadarser/ProvablyPowerfulGraphNetworks_torch","url":"https://github.com/hadarser/ProvablyPowerfulGraphNetworks_torch"},{"title":"hadarser/ProvablyPowerfulGraphNetworks","url":"https://github.com/hadarser/ProvablyPowerfulGraphNetworks"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122232,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GAT-GC (f-Scaled)","metrics":{"Accuracy":"90.44%"},"paper_url":"https://arxiv.org/abs/1907.02204v4","paper_title":"Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation","paper_date":"2019-07-04","code_links":[{"title":"zetayue/CPA","url":"https://github.com/zetayue/CPA"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":122233,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"DropGIN","metrics":{"Accuracy":"90.4%"},"paper_url":"https://arxiv.org/abs/2111.06283v1","paper_title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","paper_date":"2021-11-11","code_links":[{"title":"karolismart/dropgnn","url":"https://github.com/karolismart/dropgnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122234,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"LDP","metrics":{"Accuracy":"90.1%"},"paper_url":"https://arxiv.org/abs/1811.03508v3","paper_title":"A simple yet effective baseline for non-attributed graph classification","paper_date":"2018-11-08","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"Chen-Cai-OSU/LDP","url":"https://github.com/Chen-Cai-OSU/LDP"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122235,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"R-GCN + PANDA","metrics":{"Accuracy":"90.05%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122236,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"hGANet","metrics":{"Accuracy":"90.00%"},"paper_url":"https://arxiv.org/abs/1907.04652v1","paper_title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","paper_date":"2019-07-05","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hardgat"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122237,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"U2GNN","metrics":{"Accuracy":"89.97%"},"paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","paper_date":"2019-09-26","code_links":[{"title":"daiquocnguyen/Graph-Transformer","url":"https://github.com/daiquocnguyen/Graph-Transformer"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122238,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"FactorGCN","metrics":{"Accuracy":"89.9%","Accuracy (10-fold)":"89.9%"},"paper_url":"https://arxiv.org/abs/2010.05421v1","paper_title":"Factorizable Graph Convolutional Networks","paper_date":"2020-10-12","code_links":[{"title":"ihollywhy/FactorGCN.PyTorch","url":"https://github.com/ihollywhy/FactorGCN.PyTorch"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122239,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GFN-light","metrics":{"Accuracy":"89.89%"},"paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","paper_date":"2019-05-11","code_links":[{"title":"chentingpc/gfn","url":"https://github.com/chentingpc/gfn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122240,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GIN-0","metrics":{"Accuracy":"89.4%"},"paper_url":"http://arxiv.org/abs/1810.00826v3","paper_title":"How Powerful are Graph Neural Networks?","paper_date":"2018-10-01","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gin"},{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/gin"},{"title":"weihua916/powerful-gnns","url":"https://github.com/weihua916/powerful-gnns"},{"title":"lukecavabarrett/pna","url":"https://github.com/lukecavabarrett/pna"},{"title":"gospodima/extended-simgnn","url":"https://github.com/gospodima/extended-simgnn"},{"title":"calciver/Graph-Isomorphism-Networks","url":"https://github.com/calciver/Graph-Isomorphism-Networks"},{"title":"yuwvandy/g2gnn","url":"https://github.com/yuwvandy/g2gnn"},{"title":"PurdueMINDS/RelationalPooling","url":"https://github.com/PurdueMINDS/RelationalPooling"},{"title":"alexOarga/haiku-geometric","url":"https://github.com/alexOarga/haiku-geometric/blob/main/haiku_geometric/nn/conv/gin_conv.py"},{"title":"karolismart/dropgnn","url":"https://github.com/karolismart/dropgnn"},{"title":"egyptdj/graph-neural-mapping","url":"https://github.com/egyptdj/graph-neural-mapping"},{"title":"guillaumejaume/tuto-dl-on-graphs","url":"https://github.com/guillaumejaume/tuto-dl-on-graphs"},{"title":"pfnet-research/treewidth-prediction","url":"https://github.com/pfnet-research/treewidth-prediction"},{"title":"gmum/umwpl2021","url":"https://github.com/gmum/umwpl2021"},{"title":"zhliping/Deep-Learning","url":"https://github.com/zhliping/Deep-Learning"},{"title":"k4my4r/ECG-Classification","url":"https://github.com/k4my4r/ECG-Classification"},{"title":"igorsterner/commute-opt-gnn","url":"https://github.com/igorsterner/commute-opt-gnn"},{"title":"mfmceneaney/Lambda-GNNs","url":"https://github.com/mfmceneaney/Lambda-GNNs"},{"title":"willy-b/tiny-GIN-for-ogbg-molhiv","url":"https://github.com/willy-b/tiny-GIN-for-ogbg-molhiv"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":122241,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Multigraph ChebNet","metrics":{"Accuracy":"89.1%"},"paper_url":"http://arxiv.org/abs/1811.09595v1","paper_title":"Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules","paper_date":"2018-11-23","code_links":[{"title":"bknyaz/graph_nn","url":"https://github.com/bknyaz/graph_nn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122242,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"InfoGraph","metrics":{"Accuracy":"89.01%"},"paper_url":"https://arxiv.org/abs/1908.01000v3","paper_title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","paper_date":"2019-07-31","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/infograph"},{"title":"fanyun-sun/InfoGraph","url":"https://github.com/fanyun-sun/InfoGraph"},{"title":"yuwvandy/g2gnn","url":"https://github.com/yuwvandy/g2gnn"},{"title":"hengruizhang98/InfoGraph","url":"https://github.com/hengruizhang98/InfoGraph"},{"title":"ycremar/DIG-SSL","url":"https://github.com/ycremar/DIG-SSL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122243,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"PSCN","metrics":{"Accuracy":"88.95%"},"paper_url":"http://arxiv.org/abs/1605.05273v4","paper_title":"Learning Convolutional Neural Networks for Graphs","paper_date":"2016-05-17","code_links":[{"title":"tvayer/PSCN","url":"https://github.com/tvayer/PSCN"},{"title":"CielAl/PatchySan","url":"https://github.com/CielAl/PatchySan"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122244,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"BC + Capsules","metrics":{"Accuracy":"88.9%"},"paper_url":"http://arxiv.org/abs/1902.08399v1","paper_title":"Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations","paper_date":"2019-02-22","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122245,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"edGNN (max)","metrics":{"Accuracy":"88.8%"},"paper_url":"https://arxiv.org/abs/1904.08745v2","paper_title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","paper_date":"2019-04-18","code_links":[{"title":"guillaumejaume/edGNN","url":"https://github.com/guillaumejaume/edGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122246,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GIN + PANDA","metrics":{"Accuracy":"88.75%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122247,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"NERO","metrics":{"Accuracy":"88.68%"},"paper_url":"https://link.springer.com/chapter/10.1007/978-3-030-77964-1_18","paper_title":"Relation order histograms as a network embedding tool","paper_date":"2021-06-09","code_links":[{"title":"Prpht/NERO","url":"https://github.com/Prpht/NERO"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122248,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Path up to length h","metrics":{"Accuracy":"88.47%"},"paper_url":"https://hal-normandie-univ.archives-ouvertes.fr/hal-02053946/","paper_title":"Graph Kernels Based on Linear Patterns: Theoretical and Experimental Comparisons","paper_date":"2019-03-01","code_links":[{"title":"jajupmochi/graphkit-learn","url":"https://github.com/jajupmochi/graphkit-learn"},{"title":"jajupmochi/py-graph","url":"https://github.com/jajupmochi/py-graph"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122249,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"U2GNN (Unsupervised)","metrics":{"Accuracy":"88.47%"},"paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","paper_date":"2019-09-26","code_links":[{"title":"daiquocnguyen/Graph-Transformer","url":"https://github.com/daiquocnguyen/Graph-Transformer"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122250,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"FGW wl h=4 sp","metrics":{"Accuracy":"88.42%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122251,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"SF + RFC","metrics":{"Accuracy":"88.4%"},"paper_url":"http://arxiv.org/abs/1810.09155v2","paper_title":"A Simple Baseline Algorithm for Graph Classification","paper_date":"2018-10-22","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"edouardpineau/A-simple-baseline-algorithm-for-graph-classification","url":"https://github.com/edouardpineau/A-simple-baseline-algorithm-for-graph-classification"},{"title":"edouardpineau/Using-Laplacian-Spectrum-as-Graph-Feature-Representation","url":"https://github.com/edouardpineau/Using-Laplacian-Spectrum-as-Graph-Feature-Representation"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122252,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"ECC (5 scores)","metrics":{"Accuracy":"88.33%"},"paper_url":"http://arxiv.org/abs/1704.02901v3","paper_title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","paper_date":"2017-04-10","code_links":[{"title":"rusty1s/pytorch_cluster","url":"https://github.com/rusty1s/pytorch_cluster"},{"title":"mys007/ecc","url":"https://github.com/mys007/ecc"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122253,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"WEGL","metrics":{"Accuracy":"88.3%"},"paper_url":"https://arxiv.org/abs/2006.09430v2","paper_title":"Wasserstein Embedding for Graph Learning","paper_date":"2020-06-16","code_links":[{"title":"navid-naderi/WEGL","url":"https://github.com/navid-naderi/WEGL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122254,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"R-GIN + PANDA","metrics":{"Accuracy":"88.2%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122255,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"AWE","metrics":{"Accuracy":"87.87%"},"paper_url":"http://arxiv.org/abs/1805.11921v3","paper_title":"Anonymous Walk Embeddings","paper_date":"2018-05-30","code_links":[{"title":"nd7141/AWE","url":"https://github.com/nd7141/AWE"},{"title":"paulmorio/geo2dr","url":"https://github.com/paulmorio/geo2dr"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122256,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Graphlet Kernel","metrics":{"Accuracy":"87.7%"},"paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","paper_date":"2018-10-04","code_links":[{"title":"chrsmrrs/k-gnn","url":"https://github.com/chrsmrrs/k-gnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122257,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"CT-Layer","metrics":{"Accuracy":"87.58%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122258,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"WKPI-kcenters","metrics":{"Accuracy":"87.5%"},"paper_url":"https://arxiv.org/abs/1904.12189v2","paper_title":"Learning metrics for persistence-based summaries and applications for graph classification","paper_date":"2019-04-27","code_links":[{"title":"topology474/WKPI","url":"https://github.com/topology474/WKPI"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122259,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"DGK","metrics":{"Accuracy":"87.44%"},"paper_url":"https://www.semanticscholar.org/paper/Deep-Graph-Kernels-Yanardag-Vishwanathan/8ccd0adb1a00358ede79f1d9bdcce472dc1cb8d4","paper_title":"Deep Graph Kernels","paper_date":"2015-08-10","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122260,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"WWL","metrics":{"Accuracy":"87.27%"},"paper_url":"https://arxiv.org/abs/1906.01277v2","paper_title":"Wasserstein Weisfeiler-Lehman Graph Kernels","paper_date":"2019-06-04","code_links":[{"title":"BorgwardtLab/WWL","url":"https://github.com/BorgwardtLab/WWL"},{"title":"wenbintum/wwl-gpr","url":"https://github.com/wenbintum/wwl-gpr"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122261,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"DAGCN","metrics":{"Accuracy":"87.22%"},"paper_url":"http://arxiv.org/abs/1904.02278v1","paper_title":"DAGCN: Dual Attention Graph Convolutional Networks","paper_date":"2019-04-04","code_links":[{"title":"dawenzi123/DAGCN","url":"https://github.com/dawenzi123/DAGCN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122262,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GDL-g (SP)","metrics":{"Accuracy":"87.09%"},"paper_url":"https://arxiv.org/abs/2102.06555v2","paper_title":"Online Graph Dictionary Learning","paper_date":"2021-02-12","code_links":[{"title":"cedricvincentcuaz/GDL","url":"https://github.com/cedricvincentcuaz/GDL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122263,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"edGNN (avg)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/1904.08745v2","paper_title":"edGNN: a Simple and Powerful GNN for Directed Labeled Graphs","paper_date":"2019-04-18","code_links":[{"title":"guillaumejaume/edGNN","url":"https://github.com/guillaumejaume/edGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122264,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GAP-Layer (Rcut)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122265,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GAP-Layer (Ncut)","metrics":{"Accuracy":"86.9%"},"paper_url":"https://arxiv.org/abs/2206.07369v3","paper_title":"DiffWire: Inductive Graph Rewiring via the Lovász Bound","paper_date":"2022-06-15","code_links":[{"title":"ellisalicante/GraphRewiring-Tutorial","url":"https://github.com/ellisalicante/GraphRewiring-Tutorial"},{"title":"AdrianArnaiz/DiffWire","url":"https://github.com/AdrianArnaiz/DiffWire"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122266,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"CapsGNN","metrics":{"Accuracy":"86.67%"},"paper_url":"https://openreview.net/forum?id=Byl8BnRcYm","paper_title":"Capsule Graph Neural Network","paper_date":"2019-05-01","code_links":[{"title":"benedekrozemberczki/CapsGNN","url":"https://github.com/benedekrozemberczki/CapsGNN"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122267,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"FGW wl h=2 sp","metrics":{"Accuracy":"86.42%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122268,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"ApproxRepSet","metrics":{"Accuracy":"86.33%"},"paper_url":"https://arxiv.org/abs/1904.01962v2","paper_title":"Rep the Set: Neural Networks for Learning Set Representations","paper_date":"2019-04-03","code_links":[{"title":"giannisnik/repset","url":"https://github.com/giannisnik/repset"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122269,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"VRGC","metrics":{"Accuracy":"86.3%"},"paper_url":"https://arxiv.org/abs/1902.02721v4","paper_title":"Variational Recurrent Neural Networks for Graph Classification","paper_date":"2019-02-07","code_links":[{"title":"edouardpineau/Variational-Recurrent-Neural-Networks-for-Graph-Classification","url":"https://github.com/edouardpineau/Variational-Recurrent-Neural-Networks-for-Graph-Classification"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122270,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"k-GNN","metrics":{"Accuracy":"86.1%"},"paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","paper_date":"2018-10-04","code_links":[{"title":"chrsmrrs/k-gnn","url":"https://github.com/chrsmrrs/k-gnn"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122271,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"DGCNN","metrics":{"Accuracy":"85.83%"},"paper_url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","paper_title":"An End-to-End Deep Learning Architecture for Graph Classification","paper_date":"2018-04-29","code_links":[{"title":"muhanzhang/DGCNN","url":"https://github.com/muhanzhang/DGCNN"},{"title":"Ki-Seki/DGCNN-updated","url":"https://github.com/Ki-Seki/DGCNN-updated"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122272,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GCN + PANDA","metrics":{"Accuracy":"85.75%"},"paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","paper_date":"2024-06-06","code_links":[{"title":"jeongwhanchoi/panda","url":"https://github.com/jeongwhanchoi/panda"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":122273,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GIN-0","metrics":{"Accuracy":"85.7%"},"paper_url":"http://arxiv.org/abs/1903.02428v3","paper_title":"Fast Graph Representation Learning with PyTorch Geometric","paper_date":"2019-03-06","code_links":[{"title":"rusty1s/pytorch_geometric","url":"https://github.com/rusty1s/pytorch_geometric"},{"title":"leojklarner/gauche","url":"https://github.com/leojklarner/gauche"},{"title":"ncfrey/litmatter","url":"https://github.com/ncfrey/litmatter"},{"title":"long-9621/splinecnn","url":"https://github.com/long-9621/splinecnn"},{"title":"luxtu/OCTA-graph","url":"https://github.com/luxtu/OCTA-graph"},{"title":"NMADALI97/French-web-domain-classification","url":"https://github.com/NMADALI97/French-web-domain-classification"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":1,"source":"archive","tags":[]},{"id":122274,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"NDP","metrics":{"Accuracy":"84.7%"},"paper_url":"https://arxiv.org/abs/1910.11436v3","paper_title":"Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling","paper_date":"2019-10-24","code_links":[{"title":"danielegrattarola/decimation-pooling","url":"https://github.com/danielegrattarola/decimation-pooling"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122275,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Propagation kernels (pk)","metrics":{"Accuracy":"84.5%"},"paper_url":"https://doi.org/10.1007/s10994-015-5517-9","paper_title":"Propagation kernels: efficient graph kernels from propagated information","paper_date":"2019-02-01","code_links":[{"title":"marionmari/propagation_kernels","url":"https://github.com/marionmari/propagation_kernels"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122276,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"WL-OA","metrics":{"Accuracy":"84.5%"},"paper_url":"http://arxiv.org/abs/1606.01141v3","paper_title":"On Valid Optimal Assignment Kernels and Applications to Graph Classification","paper_date":"2016-06-03","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122277,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"SPI-GCN","metrics":{"Accuracy":"84.40%"},"paper_url":"https://hal.archives-ouvertes.fr/hal-02093451/","paper_title":"SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network","paper_date":"2019-04-08","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122278,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GMT","metrics":{"Accuracy":"83.44%"},"paper_url":"https://arxiv.org/abs/2102.11533v4","paper_title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","paper_date":"2021-02-23","code_links":[{"title":"JinheonBaek/GMT","url":"https://github.com/JinheonBaek/GMT"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122279,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Function Space Pooling","metrics":{"Accuracy":"83.3%"},"paper_url":"https://arxiv.org/abs/1905.06259v2","paper_title":"Function Space Pooling For Graph Convolutional Networks","paper_date":"2019-05-15","code_links":[],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122280,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"Function Space Pooling","metrics":{"Accuracy":"83.3%"},"paper_url":"https://arxiv.org/abs/1907.09495v2","paper_title":"IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification","paper_date":"2019-07-22","code_links":[{"title":"linmengsysu/IsoNN","url":"https://github.com/linmengsysu/IsoNN"},{"title":"jwzhanggy/isocapsnet","url":"https://github.com/jwzhanggy/isocapsnet"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122281,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"FGW raw sp","metrics":{"Accuracy":"83.26%"},"paper_url":"https://arxiv.org/abs/1805.09114v3","paper_title":"Optimal Transport for structured data with application on graphs","paper_date":"2018-05-23","code_links":[{"title":"rflamary/POT","url":"https://github.com/rflamary/POT"},{"title":"tvayer/FGW","url":"https://github.com/tvayer/FGW"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122282,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"graph2vec","metrics":{"Accuracy":"83.15% ± 9.25%"},"paper_url":"http://arxiv.org/abs/1707.05005v1","paper_title":"graph2vec: Learning Distributed Representations of Graphs","paper_date":"2017-07-17","code_links":[{"title":"benedekrozemberczki/karateclub","url":"https://github.com/benedekrozemberczki/karateclub"},{"title":"benedekrozemberczki/graph2vec","url":"https://github.com/benedekrozemberczki/graph2vec"},{"title":"MLDroid/graph2vec_tf","url":"https://github.com/MLDroid/graph2vec_tf"},{"title":"paulmorio/geo2dr","url":"https://github.com/paulmorio/geo2dr"},{"title":"compnet/pang","url":"https://github.com/compnet/pang"},{"title":"soumavaghosh/graph2vec","url":"https://github.com/soumavaghosh/graph2vec"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122283,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"EigenGCN-3","metrics":{"Accuracy":"79.5%"},"paper_url":"https://arxiv.org/abs/1904.13107v2","paper_title":"Graph Convolutional Networks with EigenPooling","paper_date":"2019-04-30","code_links":[{"title":"alge24/eigenpooling","url":"https://github.com/alge24/eigenpooling"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122284,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"GDL-g (ADJ)","metrics":{"Accuracy":"58.45%"},"paper_url":"https://arxiv.org/abs/2102.06555v2","paper_title":"Online Graph Dictionary Learning","paper_date":"2021-02-12","code_links":[{"title":"cedricvincentcuaz/GDL","url":"https://github.com/cedricvincentcuaz/GDL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122285,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"P-WL-C","metrics":{"Mean Accuracy":"90.51"},"paper_url":"http://proceedings.mlr.press/v97/rieck19a.html","paper_title":"A Persistent Weisfeiler–Lehman Procedure for Graph Classification","paper_date":"2019-06-09","code_links":[{"title":"BorgwardtLab/P-WL","url":"https://github.com/BorgwardtLab/P-WL"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":122286,"task":"Graph Classification","parent_task":"Classification","dataset":"MUTAG","model_name":"G-Tuning","metrics":{"Accuracy (10 fold)":"86.14"},"paper_url":"https://arxiv.org/abs/2312.13583v1","paper_title":"Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns","paper_date":"2023-12-21","code_links":[{"title":"zjunet/G-Tuning","url":"https://github.com/zjunet/G-Tuning"}],"metrics_order":"[\"Accuracy\", \"Accuracy (10-fold)\", \"Mean Accuracy\", \"Accuracy (10 fold)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]}]}