{"url":"/sota/node-classification-on-coauthor-cs","task":{"name":"Node Classification","url":"/task/node-classification","note":null},"dataset":{"name":"Coauthor CS","url":null},"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","Inference Time (ms)"],"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","Inference Time (ms)":"lower"}},"counts":{"rows":24,"rows_with_code":24,"rows_with_paper_page":24,"rows_dated":24,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"NCGCN","metrics":{"Accuracy":"96.64 ± 0.29"},"uses_additional_data":false,"paper_date":"2023-06-04","paper":"/paper/clarify-confused-nodes-through-separated","paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","code":"https://github.com/GISec-Team/NCGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"NCSAGE","metrics":{"Accuracy":"96.48 ± 0.25"},"uses_additional_data":false,"paper_date":"2023-06-04","paper":"/paper/clarify-confused-nodes-through-separated","paper_url":"https://arxiv.org/abs/2306.02285v6","paper_title":"Clarify Confused Nodes via Separated Learning","code":"https://github.com/GISec-Team/NCGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GraphSAGE","metrics":{"Accuracy":"96.38±0.11"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/classic-gnns-are-strong-baselines-reassessing","paper_url":"https://arxiv.org/abs/2406.08993v2","paper_title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification","code":"https://github.com/LUOyk1999/tunedGNN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"3ference","metrics":{"Accuracy":"95.99%"},"uses_additional_data":false,"paper_date":"2022-04-11","paper":"/paper/inferring-from-references-with-differences","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","code":"https://github.com/cf020031308/3ference","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"GNNMoE(GCN-like P)","metrics":{"Accuracy":"95.81±0.26"},"uses_additional_data":false,"paper_date":"2024-12-11","paper":"/paper/mixture-of-experts-meets-decoupled-message","paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","code":"https://github.com/GISec-Team/GNNMoE","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CoLinkDist","metrics":{"Accuracy":"95.80%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"CoLinkDistMLP","metrics":{"Accuracy":"95.74%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"GNNMoE(GAT-like P)","metrics":{"Accuracy":"95.72±0.23"},"uses_additional_data":false,"paper_date":"2024-12-11","paper":"/paper/mixture-of-experts-meets-decoupled-message","paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","code":"https://github.com/GISec-Team/GNNMoE","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"LinkDistMLP","metrics":{"Accuracy":"95.68%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"GNNMoE(SAGE-like P)","metrics":{"Accuracy":"95.68±0.24"},"uses_additional_data":false,"paper_date":"2024-12-11","paper":"/paper/mixture-of-experts-meets-decoupled-message","paper_url":"https://arxiv.org/abs/2412.08193v1","paper_title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","code":"https://github.com/GISec-Team/GNNMoE","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"LinkDist","metrics":{"Accuracy":"95.66%"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/distilling-self-knowledge-from-contrastive","paper_url":"https://arxiv.org/abs/2106.08541v1","paper_title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","code":"https://github.com/cf020031308/LinkDist/blob/master/ogbn.py","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"HH-GraphSAGE","metrics":{"Accuracy":"95.13%"},"uses_additional_data":false,"paper_date":"2023-08-17","paper":"/paper/half-hop-a-graph-upsampling-approach-for","paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","code":"https://github.com/nerdslab/halfhop","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"GraphSAGE","metrics":{"Accuracy":"95.11%"},"uses_additional_data":false,"paper_date":"2023-08-17","paper":"/paper/half-hop-a-graph-upsampling-approach-for","paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","code":"https://github.com/nerdslab/halfhop","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Exphormer","metrics":{"Accuracy":"94.93±0.46%"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/exphormer-sparse-transformers-for-graphs","paper_url":"https://arxiv.org/abs/2303.06147v2","paper_title":"Exphormer: Sparse Transformers for Graphs","code":"https://github.com/hamed1375/exphormer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"GCN-LPA","metrics":{"Accuracy":"94.8 ± 0.4"},"uses_additional_data":false,"paper_date":"2020-02-17","paper":"/paper/unifying-graph-convolutional-neural-networks-1","paper_url":"https://arxiv.org/abs/2002.06755v1","paper_title":"Unifying Graph Convolutional Neural Networks and Label Propagation","code":"https://github.com/hwwang55/GCN-LPA","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":12,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"HH-GCN","metrics":{"Accuracy":"94.71%"},"uses_additional_data":false,"paper_date":"2023-08-17","paper":"/paper/half-hop-a-graph-upsampling-approach-for","paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","code":"https://github.com/nerdslab/halfhop","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"GCN","metrics":{"Accuracy":"94.06%"},"uses_additional_data":false,"paper_date":"2023-08-17","paper":"/paper/half-hop-a-graph-upsampling-approach-for","paper_url":"https://arxiv.org/abs/2308.09198v1","paper_title":"Half-Hop: A graph upsampling approach for slowing down message passing","code":"https://github.com/nerdslab/halfhop","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"GCN (PPR Diffusion)","metrics":{"Accuracy":"93.01%"},"uses_additional_data":false,"paper_date":"2019-10-28","paper":"/paper/diffusion-improves-graph-learning-1","paper_url":"https://arxiv.org/abs/1911.05485v6","paper_title":"Diffusion Improves Graph Learning","code":"https://github.com/klicperajo/gdc","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"DAGNN (Ours)","metrics":{"Accuracy":"92.8%"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/towards-deeper-graph-neural-networks","paper_url":"https://arxiv.org/abs/2007.09296v1","paper_title":"Towards Deeper Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/dagnn","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":20,"model":"SIGN","metrics":{"Accuracy":"91.98 ± 0.50"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/sign-scalable-inception-graph-neural-networks","paper_url":"https://arxiv.org/abs/2004.11198v3","paper_title":"SIGN: Scalable Inception Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sign","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"GraphMix (GCN)","metrics":{"Accuracy":"91.83 ± 0.51"},"uses_additional_data":false,"paper_date":"2019-09-25","paper":"/paper/graphmix-regularized-training-of-graph-neural","paper_url":"https://arxiv.org/abs/1909.11715v3","paper_title":"GraphMix: Improved Training of GNNs for Semi-Supervised Learning","code":"https://github.com/vikasverma1077/GraphMix","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"Graph InfoClust (GIC)","metrics":{"Accuracy":"89.4 ± 0.4"},"uses_additional_data":false,"paper_date":"2020-09-15","paper":"/paper/graph-infoclust-leveraging-cluster-level-node","paper_url":"https://arxiv.org/abs/2009.06946v1","paper_title":"Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning","code":"https://github.com/cmavro/Graph-InfoClust-GIC","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"SNoRe","metrics":{"Accuracy":"88.7%"},"uses_additional_data":false,"paper_date":"2020-09-08","paper":"/paper/snore-scalable-unsupervised-learning-of","paper_url":"https://arxiv.org/abs/2009.04535v2","paper_title":"SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations","code":"https://github.com/smeznar/SNoRe","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"FIT-GNN","metrics":{"Inference Time (ms)":"0.0017"},"uses_additional_data":false,"paper_date":"2024-10-19","paper":"/paper/faster-inference-time-for-gnns-using","paper_url":"https://arxiv.org/abs/2410.15001v2","paper_title":"FIT-GNN: Faster Inference Time for GNNs Using Coarsening","code":"https://github.com/Roy-Shubhajit/FIT-GNN","n_code_links":1,"syntology":null}],"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":["Accuracy"],"entries":[{"paper":"/paper/arxiv-2601-19449","paper_title":"Fixed Aggregation Features Can Rival GNNs","arxiv_id":"2601.19449","model":"FAF bestval","row_label":"FAF bestval","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"95.37 ± 0.17"},"date":"2026-01-27","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “FAF bestval”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1 : Test accuracy on node classification: FAFs against classic GNNs.","cells":[{"column":"Accuracy","cell_text":"95.37 ± 0.17","column_header":"coauthor-cs","value":95.37,"table_index_0based":0,"row":4,"col":6}],"code":"held, no recorded run"}]},"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":15,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":11,"n_unverified":31,"n_samples":42,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":11,"n_unverified":37,"n_samples":48,"n_pointer_only_licence":8,"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"}}}