{"url":"/sota/node-classification-on-squirrel","task":{"name":"Node Classification","url":"/task/node-classification","note":null},"dataset":{"name":"Squirrel","url":"/dataset/wiki-squirrel"},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":"**Node Classification** is a machine learning task in graph-based data analysis, where the goal is to assign labels to nodes in a graph based on the properties of nodes and the relationships between them.\r\n\r\n**Node Classification** models aim to predict non-existing node properties (known as the target property) based on other node properties. Typical models used for node classification consists of a large family of graph neural networks. Model performance can be measured using benchmark datasets like [Cora](/dataset/cora), [Citeseer](/dataset/citeseer), and [Pubmed](/dataset/pubmed), among others, typically using Accuracy and F1.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Fast Graph Representation Learning With PyTorch Geometric](https://arxiv.org/pdf/1903.02428v3.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":59,"rows_with_code":44,"rows_with_paper_page":59,"rows_dated":59,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"FaberNet","metrics":{"Accuracy":"76.71±1.92"},"uses_additional_data":false,"paper_date":"2023-10-03","paper":"/paper/holonets-spectral-convolutions-do-extend-to","paper_url":"https://arxiv.org/abs/2310.02232v2","paper_title":"HoloNets: Spectral Convolutions do extend to Directed Graphs","code":"https://github.com/ChristianKoke/HoloNets","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CoED","metrics":{"Accuracy":"75.32±1.82"},"uses_additional_data":false,"paper_date":"2024-10-18","paper":"/paper/improving-graph-neural-networks-by-learning","paper_url":"https://arxiv.org/abs/2410.14109v1","paper_title":"Improving Graph Neural Networks by Learning Continuous Edge Directions","code":"https://github.com/hormoz-lab/coed-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Dir-GNN","metrics":{"Accuracy":"75.31±1.92"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/edge-directionality-improves-learning-on","paper_url":"https://arxiv.org/abs/2305.10498v3","paper_title":"Edge Directionality Improves Learning on Heterophilic Graphs","code":"https://github.com/emalgorithm/directed-graph-neural-network","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"HLP Concat","metrics":{"Accuracy":"74.17±1.83"},"uses_additional_data":false,"paper_date":"2021-06-24","paper":"/paper/simple-truncated-svd-based-model-for-node","paper_url":"https://arxiv.org/abs/2106.12807v1","paper_title":"Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"FSGNN (8-hop)","metrics":{"Accuracy":"74.10±1.89"},"uses_additional_data":false,"paper_date":"2021-05-17","paper":"/paper/improving-graph-neural-networks-with-simple","paper_url":"https://arxiv.org/abs/2105.07634v1","paper_title":"Improving Graph Neural Networks with Simple Architecture Design","code":"https://github.com/sunilkmaurya/FSGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"DJ-GNN","metrics":{"Accuracy":"73.48±1.59"},"uses_additional_data":false,"paper_date":"2023-06-29","paper":"/paper/diffusion-jump-gnns-homophiliation-via","paper_url":"https://arxiv.org/abs/2306.16976v1","paper_title":"Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters","code":"https://github.com/AhmedBegggaUA/TFM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"H2GCN+DHGR","metrics":{"Accuracy":"72.24±1.52"},"uses_additional_data":false,"paper_date":"2022-09-17","paper":"/paper/make-heterophily-graphs-better-fit-gnn-a","paper_url":"https://arxiv.org/abs/2209.08264v1","paper_title":"Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Graph ESN","metrics":{"Accuracy":"71.2±1.5"},"uses_additional_data":false,"paper_date":"2022-10-27","paper":"/paper/beyond-homophily-with-graph-echo-state-1","paper_url":"https://arxiv.org/abs/2210.15731v1","paper_title":"Beyond Homophily with Graph Echo State Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"SADE-GCN","metrics":{"Accuracy":"68.20±1.57"},"uses_additional_data":false,"paper_date":"2023-05-28","paper":"/paper/self-attention-dual-embedding-for-graphs-with","paper_url":"https://arxiv.org/abs/2305.18385v2","paper_title":"Self-attention Dual Embedding for Graphs with Heterophily","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"UDGNN (GCN)","metrics":{"Accuracy":"\t68.13±2.59"},"uses_additional_data":false,"paper_date":"2022-05-30","paper":"/paper/universal-deep-gnns-rethinking-residual","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","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"ACMII-GCN++","metrics":{"Accuracy":"67.4 ± 2.21"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"ACMII-GCN+","metrics":{"Accuracy":"67.07 ± 1.65"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"ACM-GCN++","metrics":{"Accuracy":"67.06 ± 1.66"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ACM-GCN+","metrics":{"Accuracy":"66.98 ± 1.71"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"UGT","metrics":{"Accuracy":"66.96 ±2.49"},"uses_additional_data":false,"paper_date":"2023-08-18","paper":"/paper/transitivity-preserving-graph-representation","paper_url":"https://arxiv.org/abs/2308.09517v1","paper_title":"Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-based Similarity","code":"https://github.com/nslab-cuk/unified-graph-transformer","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":21,"n_samples":26,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"RDGNN-I","metrics":{"Accuracy":"65.62 ± 2.33"},"uses_additional_data":false,"paper_date":"2024-06-16","paper":"/paper/graph-neural-reaction-diffusion-models","paper_url":"https://arxiv.org/abs/2406.10871v1","paper_title":"Graph Neural Reaction Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"SignGT","metrics":{"Accuracy":"\t64.25±1.48"},"uses_additional_data":false,"paper_date":"2023-10-17","paper":"/paper/signgt-signed-attention-based-graph","paper_url":"https://arxiv.org/abs/2310.11025v1","paper_title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"CNMPGNN","metrics":{"Accuracy":"63.60±1.96"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/cn-motifs-perceptive-graph-neural-networks","paper_url":"https://ieeexplore.ieee.org/document/9606682","paper_title":"CN-Motifs Perceptive Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"M2M-GNN","metrics":{"Accuracy":"63.60 ± 1.7"},"uses_additional_data":false,"paper_date":"2024-05-31","paper":"/paper/sign-is-not-a-remedy-multiset-to-multiset","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","code":"https://github.com/Jinx-byebye/m2mgnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"LW-GCN","metrics":{"Accuracy":"62.6±1.6"},"uses_additional_data":false,"paper_date":"2021-10-15","paper":"/paper/label-wise-message-passing-graph-neural","paper_url":"https://arxiv.org/abs/2110.08128v4","paper_title":"Label-Wise Graph Convolutional Network for Heterophilic Graphs","code":"https://github.com/enyandai/lwgcn","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"Ordered GNN","metrics":{"Accuracy":"62.44±1.96"},"uses_additional_data":false,"paper_date":"2023-02-03","paper":"/paper/ordered-gnn-ordering-message-passing-to-deal","paper_url":"https://arxiv.org/abs/2302.01524v1","paper_title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","code":"https://github.com/lumia-group/orderedgnn","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"HDP","metrics":{"Accuracy":"62.07 ± 1.57"},"uses_additional_data":false,"paper_date":"2024-05-31","paper":"/paper/heterophilous-distribution-propagation-for","paper_url":"https://arxiv.org/abs/2405.20640v1","paper_title":"Heterophilous Distribution Propagation for Graph Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"GCNH","metrics":{"Accuracy":"\t61.85±1.54"},"uses_additional_data":false,"paper_date":"2023-04-21","paper":"/paper/gcnh-a-simple-method-for-representation","paper_url":"https://arxiv.org/abs/2304.10896v1","paper_title":"GCNH: A Simple Method For Representation Learning On Heterophilous Graphs","code":"https://github.com/smartdata-polito/gcnh","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"LINKX","metrics":{"Accuracy":"61.81 ± 1.80"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/large-scale-learning-on-non-homophilous","paper_url":"https://arxiv.org/abs/2110.14446v1","paper_title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","code":"https://github.com/cuai/non-homophily-large-scale","n_code_links":5,"syntology":{"n_ran":7,"n_unverified":14,"n_samples":21,"n_pointer_only_licence":4}},{"rank_in_archive_order":25,"model":"LHS","metrics":{"Accuracy":"60.27±1.2"},"uses_additional_data":false,"paper_date":"2023-12-27","paper":"/paper/refining-latent-homophilic-structures-over","paper_url":"https://arxiv.org/abs/2312.16418v1","paper_title":"Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"CATv3-sup","metrics":{"Accuracy":"59.3±1.8"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/cat-a-causally-graph-attention-network-for","paper_url":"https://arxiv.org/abs/2312.08672v3","paper_title":"CAT: A Causally Graph Attention Network for Trimming Heterophilic Graph","code":"https://github.com/geox-lab/cat","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"NLGCN","metrics":{"Accuracy":"59.0 ± 1.2"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/non-local-graph-neural-networks","paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","code":"https://github.com/divelab/Non-Local-GNN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":28,"model":"GloGNN++","metrics":{"Accuracy":"57.88±1.76–"},"uses_additional_data":false,"paper_date":"2022-05-15","paper":"/paper/finding-global-homophily-in-graph-neural","paper_url":"https://arxiv.org/abs/2205.07308v1","paper_title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","code":"https://github.com/recklessronan/glognn","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"JKNet + Hetero-S (8 layers)","metrics":{"Accuracy":"57.83"},"uses_additional_data":false,"paper_date":"2024-06-18","paper":"/paper/the-heterophilic-snowflake-hypothesis","paper_url":"https://arxiv.org/abs/2406.12539v1","paper_title":"The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs","code":"https://github.com/bingreeky/heterosnoh","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"GloGNN","metrics":{"Accuracy":"57.54±1.39"},"uses_additional_data":false,"paper_date":"2022-05-15","paper":"/paper/finding-global-homophily-in-graph-neural","paper_url":"https://arxiv.org/abs/2205.07308v1","paper_title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","code":"https://github.com/recklessronan/glognn","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"IIE-GNN","metrics":{"Accuracy":"57.32±1.89"},"uses_additional_data":false,"paper_date":"2022-11-20","paper":"/paper/enhancing-intra-class-information-extraction","paper_url":"https://arxiv.org/abs/2211.10990v1","paper_title":"Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"NLGAT","metrics":{"Accuracy":"56.8 ± 2.5"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/non-local-graph-neural-networks","paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","code":"https://github.com/divelab/Non-Local-GNN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":33,"model":"O(d)-NSD","metrics":{"Accuracy":"56.34 ± 1.32"},"uses_additional_data":false,"paper_date":"2022-02-09","paper":"/paper/neural-sheaf-diffusion-a-topological","paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","code":"https://github.com/twitter-research/neural-sheaf-diffusion","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"LCS-GAT","metrics":{"Accuracy":"56.3 ± 2.2"},"uses_additional_data":false,"paper_date":"2022-06-06","paper":"/paper/restructuring-graph-for-higher-homophily-via","paper_url":"https://arxiv.org/abs/2206.02386v3","paper_title":"Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"GCN-RARE (λ=1.0)","metrics":{"Accuracy":"55.90±1.39"},"uses_additional_data":false,"paper_date":"2023-12-15","paper":"/paper/graphrare-reinforcement-learning-enhanced","paper_url":"https://arxiv.org/abs/2312.09708v2","paper_title":"GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"ACM-GCN","metrics":{"Accuracy":"55.19 ± 1.49"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"GGCN","metrics":{"Accuracy":"55.17 ± 1.58"},"uses_additional_data":false,"paper_date":"2021-02-12","paper":"/paper/two-sides-of-the-same-coin-heterophily-and","paper_url":"https://arxiv.org/abs/2102.06462v8","paper_title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","code":"https://github.com/yujun-yan/heterophily_and_oversmoothing","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"TE-GCNN","metrics":{"Accuracy":"55.04±1.64"},"uses_additional_data":false,"paper_date":"2024-06-08","paper":"/paper/transfer-entropy-in-graph-convolutional","paper_url":"https://arxiv.org/abs/2406.06632v1","paper_title":"Transfer Entropy in Graph Convolutional Neural Networks","code":"https://github.com/avmoldovan/Heterophily_and_oversmoothing-forked","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"Diag-NSD","metrics":{"Accuracy":"54.78 ± 1.81"},"uses_additional_data":false,"paper_date":"2022-02-09","paper":"/paper/neural-sheaf-diffusion-a-topological","paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","code":"https://github.com/twitter-research/neural-sheaf-diffusion","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"HiGNN","metrics":{"Accuracy":"54.78 ± 1.58"},"uses_additional_data":false,"paper_date":"2024-03-26","paper":"/paper/learn-from-heterophily-heterophilous","paper_url":"https://arxiv.org/abs/2403.17351v2","paper_title":"Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network","code":"https://github.com/zylMozart/HiGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"Gen-NSD","metrics":{"Accuracy":"53.17 ± 1.31"},"uses_additional_data":false,"paper_date":"2022-02-09","paper":"/paper/neural-sheaf-diffusion-a-topological","paper_url":"https://arxiv.org/abs/2202.04579v4","paper_title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs","code":"https://github.com/twitter-research/neural-sheaf-diffusion","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"ACMII-GCN","metrics":{"Accuracy":"51.8 ± 1.5"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"WRGAT","metrics":{"Accuracy":"48.85 ± 0.78"},"uses_additional_data":false,"paper_date":"2021-06-11","paper":"/paper/breaking-the-limit-of-graph-neural-networks","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","code":"https://github.com/susheels/gnns-and-local-assortativity","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":11,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"GPRGCN","metrics":{"Accuracy":"46.31 ± 2.46"},"uses_additional_data":false,"paper_date":"2020-06-14","paper":"/paper/joint-adaptive-feature-smoothing-and-topology","paper_url":"https://arxiv.org/abs/2006.07988v6","paper_title":"Adaptive Universal Generalized PageRank Graph Neural Network","code":"https://github.com/jianhao2016/GPRGNN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":45,"model":"ADPA","metrics":{"Accuracy":"45.2±1.3"},"uses_additional_data":false,"paper_date":"2023-12-07","paper":"/paper/breaking-the-entanglement-of-homophily-and","paper_url":"https://arxiv.org/abs/2312.04111v2","paper_title":"Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"Conn-NSD","metrics":{"Accuracy":"45.19±1.57"},"uses_additional_data":false,"paper_date":"2022-06-17","paper":"/paper/sheaf-neural-networks-with-connection","paper_url":"https://arxiv.org/abs/2206.08702v1","paper_title":"Sheaf Neural Networks with Connection Laplacians","code":"https://github.com/antoniopurificato/sheaf4rec","n_code_links":1,"syntology":null},{"rank_in_archive_order":47,"model":"ACM-SGC-1","metrics":{"Accuracy":"45.00 ± 1.4"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"MixHop","metrics":{"Accuracy":"43.80 ± 1.48"},"uses_additional_data":false,"paper_date":"2019-04-30","paper":"/paper/mixhop-higher-order-graph-convolution","paper_url":"https://arxiv.org/abs/1905.00067v3","paper_title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/mixhop","n_code_links":3,"syntology":null},{"rank_in_archive_order":49,"model":"ACM-SGC-2","metrics":{"Accuracy":"40.02 ± 0.96"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/revisiting-heterophily-for-graph-neural","paper_url":"https://arxiv.org/abs/2210.07606v1","paper_title":"Revisiting Heterophily For Graph Neural Networks","code":"https://github.com/SitaoLuan/ACM-GNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"Gprompt+CausalMP","metrics":{"Accuracy":"39.78±0.91"},"uses_additional_data":false,"paper_date":"2024-11-21","paper":"/paper/heterophilic-graph-neural-networks","paper_url":"https://arxiv.org/abs/2411.13821v2","paper_title":"Heterophilic Graph Neural Networks Optimization with Causal Message-passing","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"GCNII","metrics":{"Accuracy":"38.47 ± 1.58"},"uses_additional_data":false,"paper_date":"2020-07-04","paper":"/paper/simple-and-deep-graph-convolutional-networks-1","paper_url":"https://arxiv.org/abs/2007.02133v1","paper_title":"Simple and Deep Graph Convolutional Networks","code":"https://github.com/chennnM/GCNII/tree/master/PyG/ogbn-arxiv","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}},{"rank_in_archive_order":52,"model":"Geom-GCN-P","metrics":{"Accuracy":"38.14"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/geom-gcn-geometric-graph-convolutional-1","paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","code":"https://github.com/bingzhewei/geom-gcn","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":53,"model":"SDRF","metrics":{"Accuracy":"37.05±0.17"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/understanding-over-squashing-and-bottlenecks-1","paper_url":"https://arxiv.org/abs/2111.14522v3","paper_title":"Understanding over-squashing and bottlenecks on graphs via curvature","code":"https://github.com/jctops/understanding-oversquashing","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"Geom-GCN-S","metrics":{"Accuracy":"36.24"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/geom-gcn-geometric-graph-convolutional-1","paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","code":"https://github.com/bingzhewei/geom-gcn","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":55,"model":"NLMLP","metrics":{"Accuracy":"33.7 ± 1.5"},"uses_additional_data":false,"paper_date":"2020-05-29","paper":"/paper/non-local-graph-neural-networks","paper_url":"https://arxiv.org/abs/2005.14612v2","paper_title":"Non-Local Graph Neural Networks","code":"https://github.com/divelab/Non-Local-GNN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":56,"model":"Geom-GCN-I","metrics":{"Accuracy":"33.32"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/geom-gcn-geometric-graph-convolutional-1","paper_url":"https://arxiv.org/abs/2002.05287v2","paper_title":"Geom-GCN: Geometric Graph Convolutional Networks","code":"https://github.com/bingzhewei/geom-gcn","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":57,"model":"H2GCN-2","metrics":{"Accuracy":"32.33 ± 1.94"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/generalizing-graph-neural-networks-beyond","paper_url":"https://arxiv.org/abs/2006.11468v2","paper_title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","code":"https://github.com/GemsLab/H2GCN","n_code_links":4,"syntology":{"n_ran":13,"n_unverified":8,"n_samples":21,"n_pointer_only_licence":6}},{"rank_in_archive_order":58,"model":"FAGCN","metrics":{"Accuracy":"30.83 ± 0.69"},"uses_additional_data":false,"paper_date":"2021-01-04","paper":"/paper/beyond-low-frequency-information-in-graph","paper_url":"https://arxiv.org/abs/2101.00797v1","paper_title":"Beyond Low-frequency Information in Graph Convolutional Networks","code":"https://github.com/bdy9527/FAGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":59,"model":"H2GCN-1","metrics":{"Accuracy":"28.98 ± 1.97"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/generalizing-graph-neural-networks-beyond","paper_url":"https://arxiv.org/abs/2006.11468v2","paper_title":"Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs","code":"https://github.com/GemsLab/H2GCN","n_code_links":4,"syntology":{"n_ran":13,"n_unverified":8,"n_samples":21,"n_pointer_only_licence":6}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":29,"rows_with_any_sample_ran":24,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":52,"n_unverified":81,"n_samples":133,"n_pointer_only_licence":27,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":99,"n_unverified":126,"n_samples":225,"n_pointer_only_licence":53,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}