{"task":"Node Classification","dataset":"Texas","metric_names":["Accuracy"],"rows":[{"id":96524,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"RDGNN-S","metrics":{"Accuracy":"94.59 ± 5.97"},"paper_url":"https://arxiv.org/abs/2406.10871v1","paper_title":"Graph Neural Reaction Diffusion Models","paper_date":"2024-06-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96525,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"RDGNN-I","metrics":{"Accuracy":"93.51 ± 5.93"},"paper_url":"https://arxiv.org/abs/2406.10871v1","paper_title":"Graph Neural Reaction Diffusion Models","paper_date":"2024-06-16","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96526,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"MGNN + Hetero-S (8 layers)","metrics":{"Accuracy":"93.09"},"paper_url":"https://arxiv.org/abs/2406.12539v1","paper_title":"The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs","paper_date":"2024-06-18","code_links":[{"title":"bingreeky/heterosnoh","url":"https://github.com/bingreeky/heterosnoh"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96527,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"2-HiGCN","metrics":{"Accuracy":"92.45±0.73"},"paper_url":"https://arxiv.org/abs/2309.12971v2","paper_title":"Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes","paper_date":"2023-09-22","code_links":[{"title":"yiminghh/higcn","url":"https://github.com/yiminghh/higcn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96528,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"DJ-GNN","metrics":{"Accuracy":"92.43±3.15"},"paper_url":"https://arxiv.org/abs/2306.16976v1","paper_title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","paper_date":"2023-06-29","code_links":[{"title":"AhmedBegggaUA/TFM","url":"https://github.com/AhmedBegggaUA/TFM"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96529,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"M2M-GNN","metrics":{"Accuracy":"89.19 ± 4.5"},"paper_url":"https://arxiv.org/abs/2405.20652v1","paper_title":"Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs","paper_date":"2024-05-31","code_links":[{"title":"Jinx-byebye/m2mgnn","url":"https://github.com/Jinx-byebye/m2mgnn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96530,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACM-GCN+","metrics":{"Accuracy":"88.38 ± 3.64"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96531,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACM-GCN++","metrics":{"Accuracy":"88.38 ±  3.43"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96532,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACMII-GCN++","metrics":{"Accuracy":"88.38 ± 3.43"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96533,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GRADE-GAT","metrics":{"Accuracy":"88.3±3.5"},"paper_url":"https://arxiv.org/abs/2403.20221v1","paper_title":"Graph Neural Aggregation-diffusion with Metastability","paper_date":"2024-03-29","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96534,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACMII-GCN+","metrics":{"Accuracy":"88.11 ± 3.24"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96535,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACM-GCN","metrics":{"Accuracy":"87.84 ± 4.4"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96536,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GCNH","metrics":{"Accuracy":"87.84±3.87"},"paper_url":"https://arxiv.org/abs/2304.10896v1","paper_title":"GCNH: A Simple Method For Representation Learning On Heterophilous Graphs","paper_date":"2023-04-21","code_links":[{"title":"smartdata-polito/gcnh","url":"https://github.com/smartdata-polito/gcnh"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96537,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"HLP Concat","metrics":{"Accuracy":"87.57 ± 5.44"},"paper_url":"https://arxiv.org/abs/2106.12807v1","paper_title":"Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs","paper_date":"2021-06-24","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96538,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"FSGNN","metrics":{"Accuracy":"87.30 ± 5.55"},"paper_url":"https://arxiv.org/abs/2105.07634v1","paper_title":"Improving Graph Neural Networks with Simple Architecture Design","paper_date":"2021-05-17","code_links":[{"title":"sunilkmaurya/FSGNN","url":"https://github.com/sunilkmaurya/FSGNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96539,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACMII-GCN","metrics":{"Accuracy":"86.76 ± 4.75"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96540,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"H2GCN-RARE (λ=1.0)","metrics":{"Accuracy":"86.76±5.80"},"paper_url":"https://arxiv.org/abs/2312.09708v2","paper_title":"GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy","paper_date":"2023-12-15","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96541,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"UGT","metrics":{"Accuracy":"86.67 ±8.31"},"paper_url":"https://arxiv.org/abs/2308.09517v1","paper_title":"Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity","paper_date":"2023-08-18","code_links":[{"title":"nslab-cuk/unified-graph-transformer","url":"https://github.com/nslab-cuk/unified-graph-transformer"},{"title":"nslab-cuk/community-aware-graph-transformer","url":"https://github.com/nslab-cuk/community-aware-graph-transformer"},{"title":"nslab-cuk/literalkg","url":"https://github.com/nslab-cuk/literalkg"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96542,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GraphSAGE + UniGAP","metrics":{"Accuracy":"86.52 ± 4.8"},"paper_url":"https://arxiv.org/abs/2407.19420v1","paper_title":"UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks","paper_date":"2024-07-28","code_links":[{"title":"wangxiaotang0906/unigap","url":"https://github.com/wangxiaotang0906/unigap"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96543,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"SADE-GCN","metrics":{"Accuracy":"86.49±5.12"},"paper_url":"https://arxiv.org/abs/2305.18385v2","paper_title":"Self-attention Dual Embedding for Graphs with Heterophily","paper_date":"2023-05-28","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96544,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"LHS","metrics":{"Accuracy":"86.32±4.5"},"paper_url":"https://arxiv.org/abs/2312.16418v1","paper_title":"Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks","paper_date":"2023-12-27","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96545,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Ordered GNN","metrics":{"Accuracy":"86.22±4.12"},"paper_url":"https://arxiv.org/abs/2302.01524v1","paper_title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","paper_date":"2023-02-03","code_links":[{"title":"lumia-group/orderedgnn","url":"https://github.com/lumia-group/orderedgnn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96546,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"HiGNN","metrics":{"Accuracy":"86.22 ± 4.67"},"paper_url":"https://arxiv.org/abs/2403.17351v2","paper_title":"Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network","paper_date":"2024-03-26","code_links":[{"title":"zylMozart/HiGNN","url":"https://github.com/zylMozart/HiGNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96547,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Conn-NSD","metrics":{"Accuracy":"86.16±2.24 "},"paper_url":"https://arxiv.org/abs/2206.08702v1","paper_title":"Sheaf Neural Networks with Connection Laplacians","paper_date":"2022-06-17","code_links":[{"title":"antoniopurificato/sheaf4rec","url":"https://github.com/antoniopurificato/sheaf4rec"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96548,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"O(d)-NSD","metrics":{"Accuracy":"85.95 ± 5.51"},"paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","paper_date":"2022-02-09","code_links":[{"title":"twitter-research/neural-sheaf-diffusion","url":"https://github.com/twitter-research/neural-sheaf-diffusion"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96549,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"IIE-GNN","metrics":{"Accuracy":"85.84±4.23"},"paper_url":"https://arxiv.org/abs/2211.10990v1","paper_title":"Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach","paper_date":"2022-11-20","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96550,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"CNMPGNN","metrics":{"Accuracy":"85.68±5.28"},"paper_url":"https://ieeexplore.ieee.org/document/9606682","paper_title":"CN-Motifs Perceptive Graph Neural Networks","paper_date":"2021-11-15","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96551,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Diag-NSD","metrics":{"Accuracy":"85.67 ± 6.95"},"paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","paper_date":"2022-02-09","code_links":[{"title":"twitter-research/neural-sheaf-diffusion","url":"https://github.com/twitter-research/neural-sheaf-diffusion"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96552,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"NLMLP ","metrics":{"Accuracy":"85.4 ± 3.8"},"paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","paper_date":"2020-05-29","code_links":[{"title":"divelab/Non-Local-GNN","url":"https://github.com/divelab/Non-Local-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96553,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"UniG-Encoder","metrics":{"Accuracy":"85.40±5.3"},"paper_url":"https://arxiv.org/abs/2308.01650v1","paper_title":"UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification","paper_date":"2023-08-03","code_links":[{"title":"minhzou/unig-encoder","url":"https://github.com/minhzou/unig-encoder"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96554,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GGCN","metrics":{"Accuracy":"84.86 ± 4.55"},"paper_url":"https://arxiv.org/abs/2102.06462v8","paper_title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","paper_date":"2021-02-12","code_links":[{"title":"yujun-yan/heterophily_and_oversmoothing","url":"https://github.com/yujun-yan/heterophily_and_oversmoothing"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96555,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"H2GCN+DHGR","metrics":{"Accuracy":"84.86±5.01"},"paper_url":"https://arxiv.org/abs/2209.08264v1","paper_title":"Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach","paper_date":"2022-09-17","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96556,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"TE-GCNN","metrics":{"Accuracy":"84.86 ± 4.55"},"paper_url":"https://arxiv.org/abs/2406.06632v1","paper_title":"Transfer Entropy in Graph Convolutional Neural Networks","paper_date":"2024-06-08","code_links":[{"title":"avmoldovan/Heterophily_and_oversmoothing-forked","url":"https://github.com/avmoldovan/Heterophily_and_oversmoothing-forked"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96557,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"UDGNN (GCN)","metrics":{"Accuracy":"84.60±5.32"},"paper_url":"https://arxiv.org/abs/2205.15127v1","paper_title":"Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing","paper_date":"2022-05-30","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96558,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"CoED","metrics":{"Accuracy":"\t84.59±4.53"},"paper_url":"https://arxiv.org/abs/2410.14109v1","paper_title":"Improving Graph Neural Networks by Learning Continuous Edge Directions","paper_date":"2024-10-18","code_links":[{"title":"hormoz-lab/coed-gnn","url":"https://github.com/hormoz-lab/coed-gnn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96559,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GloGNN","metrics":{"Accuracy":"84.32±4.15"},"paper_url":"https://arxiv.org/abs/2205.07308v1","paper_title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","paper_date":"2022-05-15","code_links":[{"title":"recklessronan/glognn","url":"https://github.com/recklessronan/glognn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96560,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Graph ESN","metrics":{"Accuracy":"84.3±4.4"},"paper_url":"https://arxiv.org/abs/2210.15731v1","paper_title":"Beyond Homophily with Graph Echo State Networks","paper_date":"2022-10-27","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96561,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GloGNN++","metrics":{"Accuracy":"84.05±4.90"},"paper_url":"https://arxiv.org/abs/2205.07308v1","paper_title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","paper_date":"2022-05-15","code_links":[{"title":"recklessronan/glognn","url":"https://github.com/recklessronan/glognn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96562,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ChebNet+Bregman","metrics":{"Accuracy":"84.05 ± 5.47"},"paper_url":"https://arxiv.org/abs/2309.06645v1","paper_title":"Bregman Graph Neural Network","paper_date":"2023-09-12","code_links":[{"title":"jiayuzhai1207/bregmangnn","url":"https://github.com/jiayuzhai1207/bregmangnn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96563,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ADPA","metrics":{"Accuracy":"\t83.8±2.7"},"paper_url":"https://arxiv.org/abs/2312.04111v2","paper_title":"Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification","paper_date":"2023-12-07","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96564,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"WRGAT","metrics":{"Accuracy":"83.62 ± 5.50"},"paper_url":"https://arxiv.org/abs/2106.06586v1","paper_title":"Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns","paper_date":"2021-06-11","code_links":[{"title":"susheels/gnns-and-local-assortativity","url":"https://github.com/susheels/gnns-and-local-assortativity"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96565,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"H2GCN-1","metrics":{"Accuracy":"83.24 ± 7.07"},"paper_url":"https://arxiv.org/abs/2006.11468v2","paper_title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","paper_date":"2020-06-20","code_links":[{"title":"GemsLab/H2GCN","url":"https://github.com/GemsLab/H2GCN"},{"title":"GitEventhandler/H2GCN-PyTorch","url":"https://github.com/GitEventhandler/H2GCN-PyTorch"},{"title":"sxwee/GNNsIMPL","url":"https://github.com/sxwee/GNNsIMPL/tree/main/H2GCN"},{"title":"kdd-submitter/on_local_aggregation","url":"https://github.com/kdd-submitter/on_local_aggregation"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96566,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"TDGNN-w","metrics":{"Accuracy":"83.00 ± 4.50"},"paper_url":"https://arxiv.org/abs/2108.11022v1","paper_title":"Tree Decomposed Graph Neural Network","paper_date":"2021-08-25","code_links":[{"title":"YuWVandy/TDGNN","url":"https://github.com/YuWVandy/TDGNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96567,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"CATv3-sup","metrics":{"Accuracy":"83.0±2.5"},"paper_url":"https://arxiv.org/abs/2312.08672v3","paper_title":"CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph","paper_date":"2023-12-14","code_links":[{"title":"geox-lab/cat","url":"https://github.com/geox-lab/cat"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96568,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Gen-NSD","metrics":{"Accuracy":"82.97 ± 5.13"},"paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","paper_date":"2022-02-09","code_links":[{"title":"twitter-research/neural-sheaf-diffusion","url":"https://github.com/twitter-research/neural-sheaf-diffusion"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96569,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACM-SGC-1","metrics":{"Accuracy":"81.89 ± 4.53"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96570,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"ACM-SGC-2","metrics":{"Accuracy":"81.89 ± 4.53"},"paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","paper_date":"2022-10-14","code_links":[{"title":"SitaoLuan/ACM-GNN","url":"https://github.com/SitaoLuan/ACM-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96571,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GPRGCN","metrics":{"Accuracy":"81.35 ± 5.32"},"paper_url":"https://arxiv.org/abs/2006.07988v6","paper_title":"Adaptive Universal Generalized PageRank Graph Neural Network","paper_date":"2020-06-14","code_links":[{"title":"jianhao2016/GPRGNN","url":"https://github.com/jianhao2016/GPRGNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96572,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"FDGATII","metrics":{"Accuracy":"80.5405"},"paper_url":"https://arxiv.org/abs/2110.11464v2","paper_title":"FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping","paper_date":"2021-10-21","code_links":[{"title":"gayanku/FDGATII","url":"https://github.com/gayanku/FDGATII"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96573,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"H2GCN-2","metrics":{"Accuracy":"80.00 ± 6.77"},"paper_url":"https://arxiv.org/abs/2006.11468v2","paper_title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","paper_date":"2020-06-20","code_links":[{"title":"GemsLab/H2GCN","url":"https://github.com/GemsLab/H2GCN"},{"title":"GitEventhandler/H2GCN-PyTorch","url":"https://github.com/GitEventhandler/H2GCN-PyTorch"},{"title":"sxwee/GNNsIMPL","url":"https://github.com/sxwee/GNNsIMPL/tree/main/H2GCN"},{"title":"kdd-submitter/on_local_aggregation","url":"https://github.com/kdd-submitter/on_local_aggregation"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96574,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"MixHop","metrics":{"Accuracy":"77.84 ± 7.73"},"paper_url":"https://arxiv.org/abs/1905.00067v3","paper_title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","paper_date":"2019-04-30","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/mixhop"},{"title":"benedekrozemberczki/MixHop-and-N-GCN","url":"https://github.com/benedekrozemberczki/MixHop-and-N-GCN"},{"title":"samihaija/mixhop","url":"https://github.com/samihaija/mixhop"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96575,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"GCNII","metrics":{"Accuracy":"77.57 ± 3.83"},"paper_url":"https://arxiv.org/abs/2007.02133v1","paper_title":"Simple and Deep Graph Convolutional Networks","paper_date":"2020-07-04","code_links":[{"title":"chennnM/GCNII","url":"https://github.com/chennnM/GCNII/tree/master/PyG/ogbn-arxiv"},{"title":"chennnM/GCNII","url":"https://github.com/chennnM/GCNII"},{"title":"zhanglab-aim/cancer-net","url":"https://github.com/zhanglab-aim/cancer-net"},{"title":"tyxxzjpdez/GCNII-DropGroups","url":"https://github.com/tyxxzjpdez/GCNII-DropGroups"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96576,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"FAGCN","metrics":{"Accuracy":"76.49 ± 2.87"},"paper_url":"https://arxiv.org/abs/2101.00797v1","paper_title":"Beyond Low-frequency Information in Graph Convolutional Networks","paper_date":"2021-01-04","code_links":[{"title":"bdy9527/FAGCN","url":"https://github.com/bdy9527/FAGCN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96577,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"LINKX","metrics":{"Accuracy":"74.60 ± 8.37"},"paper_url":"https://arxiv.org/abs/2110.14446v1","paper_title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","paper_date":"2021-10-27","code_links":[{"title":"cuai/non-homophily-large-scale","url":"https://github.com/cuai/non-homophily-large-scale"},{"title":"CUAI/Non-Homophily-Benchmarks","url":"https://github.com/CUAI/Non-Homophily-Benchmarks"},{"title":"ivam-he/chebnetii","url":"https://github.com/ivam-he/chebnetii"},{"title":"kkhuang81/UniFilter","url":"https://github.com/kkhuang81/UniFilter"},{"title":"kkhuang81/AdaptKry","url":"https://github.com/kkhuang81/AdaptKry"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96578,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"DeltaGNN constant","metrics":{"Accuracy":"74.05±3.08"},"paper_url":"https://arxiv.org/abs/2501.06002v1","paper_title":"DeltaGNN: Graph Neural Network with Information Flow Control","paper_date":"2025-01-10","code_links":[{"title":"basiralab/deltagnn","url":"https://github.com/basiralab/deltagnn"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96579,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Geom-GCN-P","metrics":{"Accuracy":"67.57"},"paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","paper_date":"2020-02-13","code_links":[{"title":"bingzhewei/geom-gcn","url":"https://github.com/bingzhewei/geom-gcn"},{"title":"graphdml-uiuc-jlu/geom-gcn","url":"https://github.com/graphdml-uiuc-jlu/geom-gcn"},{"title":"alexfanjn/geomgcn_pyg","url":"https://github.com/alexfanjn/geomgcn_pyg"},{"title":"KAIDI3270/Geom_GCN_pytorch_implementation","url":"https://github.com/KAIDI3270/Geom_GCN_pytorch_implementation"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96580,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"NLGCN ","metrics":{"Accuracy":"65.5 ± 6.6"},"paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","paper_date":"2020-05-29","code_links":[{"title":"divelab/Non-Local-GNN","url":"https://github.com/divelab/Non-Local-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96581,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"SDRF","metrics":{"Accuracy":"64.46±0.38"},"paper_url":"https://arxiv.org/abs/2111.14522v3","paper_title":"Understanding over-squashing and bottlenecks on graphs via curvature","paper_date":"2021-11-29","code_links":[{"title":"jctops/understanding-oversquashing","url":"https://github.com/jctops/understanding-oversquashing"},{"title":"josephjwilson/cayley_graph_propagation","url":"https://github.com/josephjwilson/cayley_graph_propagation"},{"title":"harel147/REFine","url":"https://github.com/harel147/REFine"},{"title":"cedric_sanders/masterarbeit","url":"https://gitlab.com/cedric_sanders/masterarbeit"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96582,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"NLGAT ","metrics":{"Accuracy":"62.6 ± 7.1"},"paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","paper_date":"2020-05-29","code_links":[{"title":"divelab/Non-Local-GNN","url":"https://github.com/divelab/Non-Local-GNN"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96583,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Geom-GCN-S","metrics":{"Accuracy":"59.73"},"paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","paper_date":"2020-02-13","code_links":[{"title":"bingzhewei/geom-gcn","url":"https://github.com/bingzhewei/geom-gcn"},{"title":"graphdml-uiuc-jlu/geom-gcn","url":"https://github.com/graphdml-uiuc-jlu/geom-gcn"},{"title":"alexfanjn/geomgcn_pyg","url":"https://github.com/alexfanjn/geomgcn_pyg"},{"title":"KAIDI3270/Geom_GCN_pytorch_implementation","url":"https://github.com/KAIDI3270/Geom_GCN_pytorch_implementation"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96584,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"Geom-GCN-I","metrics":{"Accuracy":"57.58"},"paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","paper_date":"2020-02-13","code_links":[{"title":"bingzhewei/geom-gcn","url":"https://github.com/bingzhewei/geom-gcn"},{"title":"graphdml-uiuc-jlu/geom-gcn","url":"https://github.com/graphdml-uiuc-jlu/geom-gcn"},{"title":"alexfanjn/geomgcn_pyg","url":"https://github.com/alexfanjn/geomgcn_pyg"},{"title":"KAIDI3270/Geom_GCN_pytorch_implementation","url":"https://github.com/KAIDI3270/Geom_GCN_pytorch_implementation"}],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]},{"id":96585,"task":"Node Classification","parent_task":null,"dataset":"Texas","model_name":"LINKX+CausalMP","metrics":{"Accuracy":"57.36±0.60"},"paper_url":"https://arxiv.org/abs/2411.13821v2","paper_title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","paper_date":"2024-11-21","code_links":[],"metrics_order":"[\"Accuracy\"]","area":"Graphs","uses_additional_data":0,"source":"archive","tags":[]}]}