{"task":"Node Classification","dataset":"Coauthor CS","metric_names":["Accuracy","Inference Time (ms)"],"rows":[{"id":96298,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"NCGCN","metrics":{"Accuracy":"96.64 ± 0.29"},"paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","paper_date":"2023-06-04","code_links":[{"title":"GISec-Team/NCGNN","url":"https://github.com/GISec-Team/NCGNN"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96299,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"NCSAGE","metrics":{"Accuracy":"96.48 ± 0.25"},"paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","paper_date":"2023-06-04","code_links":[{"title":"GISec-Team/NCGNN","url":"https://github.com/GISec-Team/NCGNN"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96300,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GraphSAGE","metrics":{"Accuracy":"96.38±0.11"},"paper_url":"https://arxiv.org/abs/2406.08993v2","paper_title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification","paper_date":"2024-06-13","code_links":[{"title":"LUOyk1999/tunedGNN","url":"https://github.com/LUOyk1999/tunedGNN"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96301,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"3ference","metrics":{"Accuracy":"95.99%"},"paper_url":"https://www.mdpi.com/2227-7390/10/8/1262/htm","paper_title":"Inferring from References with Differences for Semi-Supervised Node Classification on Graphs","paper_date":"2022-04-11","code_links":[{"title":"cf020031308/3ference","url":"https://github.com/cf020031308/3ference"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96302,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GNNMoE(GCN-like P)","metrics":{"Accuracy":"95.81±0.26"},"paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","paper_date":"2024-12-11","code_links":[{"title":"GISec-Team/GNNMoE","url":"https://github.com/GISec-Team/GNNMoE"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96303,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"CoLinkDist","metrics":{"Accuracy":"95.80%"},"paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","paper_date":"2021-06-16","code_links":[{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py"},{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96304,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"CoLinkDistMLP","metrics":{"Accuracy":"95.74%"},"paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","paper_date":"2021-06-16","code_links":[{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py"},{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96305,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GNNMoE(GAT-like P)","metrics":{"Accuracy":"95.72±0.23"},"paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","paper_date":"2024-12-11","code_links":[{"title":"GISec-Team/GNNMoE","url":"https://github.com/GISec-Team/GNNMoE"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96306,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"LinkDistMLP","metrics":{"Accuracy":"95.68%"},"paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","paper_date":"2021-06-16","code_links":[{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py"},{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96307,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GNNMoE(SAGE-like P)","metrics":{"Accuracy":"95.68±0.24"},"paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","paper_date":"2024-12-11","code_links":[{"title":"GISec-Team/GNNMoE","url":"https://github.com/GISec-Team/GNNMoE"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96308,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"LinkDist","metrics":{"Accuracy":"95.66%"},"paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","paper_date":"2021-06-16","code_links":[{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py"},{"title":"cf020031308/LinkDist","url":"https://github.com/cf020031308/LinkDist"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96309,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"HH-GraphSAGE","metrics":{"Accuracy":"95.13%"},"paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","paper_date":"2023-08-17","code_links":[{"title":"nerdslab/halfhop","url":"https://github.com/nerdslab/halfhop"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96310,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GraphSAGE","metrics":{"Accuracy":"95.11%"},"paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","paper_date":"2023-08-17","code_links":[{"title":"nerdslab/halfhop","url":"https://github.com/nerdslab/halfhop"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96311,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"Exphormer","metrics":{"Accuracy":"94.93±0.46%"},"paper_url":"https://arxiv.org/abs/2303.06147v2","paper_title":"Exphormer: Sparse Transformers for Graphs","paper_date":"2023-03-10","code_links":[{"title":"hamed1375/exphormer","url":"https://github.com/hamed1375/exphormer"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96312,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GCN-LPA","metrics":{"Accuracy":"94.8 ± 0.4"},"paper_url":"https://arxiv.org/abs/2002.06755v1","paper_title":"Unifying Graph Convolutional Neural Networks and Label Propagation","paper_date":"2020-02-17","code_links":[{"title":"hwwang55/GCN-LPA","url":"https://github.com/hwwang55/GCN-LPA"},{"title":"achalagarwal/gcn-lpa","url":"https://github.com/achalagarwal/gcn-lpa"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96313,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"HH-GCN","metrics":{"Accuracy":"94.71%"},"paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","paper_date":"2023-08-17","code_links":[{"title":"nerdslab/halfhop","url":"https://github.com/nerdslab/halfhop"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96314,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GCN","metrics":{"Accuracy":"94.06%"},"paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","paper_date":"2023-08-17","code_links":[{"title":"nerdslab/halfhop","url":"https://github.com/nerdslab/halfhop"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96315,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GCN (PPR Diffusion)","metrics":{"Accuracy":"93.01%"},"paper_url":"https://arxiv.org/abs/1911.05485v6","paper_title":"Diffusion Improves Graph Learning","paper_date":"2019-10-28","code_links":[{"title":"klicperajo/gdc","url":"https://github.com/klicperajo/gdc"},{"title":"jhngjng/naq-pytorch","url":"https://github.com/jhngjng/naq-pytorch"},{"title":"hazdzz/GDC","url":"https://github.com/hazdzz/GDC"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96316,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"DAGNN (Ours)","metrics":{"Accuracy":"92.8%"},"paper_url":"https://arxiv.org/abs/2007.09296v1","paper_title":"Towards Deeper Graph Neural Networks","paper_date":"2020-07-18","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/dagnn"},{"title":"mengliu1998/DeeperGNN","url":"https://github.com/mengliu1998/DeeperGNN"},{"title":"divelab/DeeperGNN","url":"https://github.com/divelab/DeeperGNN"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96317,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"SIGN","metrics":{"Accuracy":"91.98 ± 0.50"},"paper_url":"https://arxiv.org/abs/2004.11198v3","paper_title":"SIGN: Scalable Inception Graph Neural Networks","paper_date":"2020-04-23","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sign"},{"title":"twitter-research/sign","url":"https://github.com/twitter-research/sign"},{"title":"facebookresearch/NARS","url":"https://github.com/facebookresearch/NARS"},{"title":"basiralab/falcon","url":"https://github.com/basiralab/falcon"},{"title":"MindSpore-paper-code-2/code400","url":"https://github.com/MindSpore-paper-code-2/code400/tree/main/Inception/inceptionv4"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96318,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"GraphMix (GCN)","metrics":{"Accuracy":"91.83 ± 0.51"},"paper_url":"https://arxiv.org/abs/1909.11715v3","paper_title":"GraphMix: Improved Training of GNNs for Semi-Supervised Learning","paper_date":"2019-09-25","code_links":[{"title":"vikasverma1077/GraphMix","url":"https://github.com/vikasverma1077/GraphMix"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96319,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"Graph InfoClust (GIC)","metrics":{"Accuracy":"89.4 ± 0.4"},"paper_url":"https://arxiv.org/abs/2009.06946v1","paper_title":"Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning","paper_date":"2020-09-15","code_links":[{"title":"cmavro/Graph-InfoClust-GIC","url":"https://github.com/cmavro/Graph-InfoClust-GIC"},{"title":"cmavro/HeMI","url":"https://github.com/cmavro/HeMI"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96320,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"SNoRe","metrics":{"Accuracy":"88.7%"},"paper_url":"https://arxiv.org/abs/2009.04535v2","paper_title":"SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations","paper_date":"2020-09-08","code_links":[{"title":"smeznar/SNoRe","url":"https://github.com/smeznar/SNoRe"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96321,"task":"Node Classification","parent_task":null,"dataset":"Coauthor CS","model_name":"FIT-GNN","metrics":{"Inference Time (ms)":"0.0017"},"paper_url":"https://arxiv.org/abs/2410.15001v2","paper_title":"FIT-GNN: Faster Inference Time for GNNs Using Coarsening","paper_date":"2024-10-19","code_links":[{"title":"Roy-Shubhajit/FIT-GNN","url":"https://github.com/Roy-Shubhajit/FIT-GNN"}],"metrics_order":"[\"Accuracy\", \"Inference Time (ms)\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]}]}