{"url":"/sota/node-classification-on-pubmed-with-public","task":{"name":"Node Classification","url":"/task/node-classification","note":null},"dataset":{"name":"PubMed with Public Split: fixed 20 nodes per class","url":"/dataset/pubmed"},"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":37,"rows_with_code":36,"rows_with_paper_page":36,"rows_dated":36,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"OGC","metrics":{"Accuracy":"83.4%"},"uses_additional_data":false,"paper_date":"2023-09-24","paper":"/paper/from-cluster-assumption-to-graph-convolution","paper_url":"https://arxiv.org/abs/2309.13599v2","paper_title":"From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited","code":"https://github.com/zhengwang100/ogc_ggcm","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"CPF-tra-GCNII","metrics":{"Accuracy":"83.20%"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/extract-the-knowledge-of-graph-neural","paper_url":"https://arxiv.org/abs/2103.02885v1","paper_title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","code":"https://github.com/BUPT-GAMMA/CPF","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":3,"model":"GRAND","metrics":{"Accuracy":"82.7 ± 0.6"},"uses_additional_data":false,"paper_date":"2020-05-22","paper":"/paper/graph-random-neural-network","paper_url":"https://arxiv.org/abs/2005.11079v4","paper_title":"Graph Random Neural Network for Semi-Supervised Learning on Graphs","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/grand","n_code_links":9,"syntology":{"n_ran":8,"n_unverified":14,"n_samples":22,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"Graph-MLP + ASAM","metrics":{"Accuracy":"82.60 ± 0.80%"},"uses_additional_data":false,"paper_date":"2023-06-15","paper":"/paper/the-split-matters-flat-minima-methods-for","paper_url":"https://arxiv.org/abs/2306.09121v1","paper_title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","code":"https://github.com/foisunt/fmms-in-gnns","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DSGCN","metrics":{"Accuracy":"81.9%"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/bridging-the-gap-between-spectral-and-spatial","paper_url":"https://arxiv.org/abs/2003.11702v1","paper_title":"Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks","code":"https://github.com/balcilar/Spectral-Designed-Graph-Convolutions","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"Truncated Krylov","metrics":{"Accuracy":"81.7%"},"uses_additional_data":false,"paper_date":"2019-06-05","paper":"/paper/break-the-ceiling-stronger-multi-scale-deep","paper_url":"https://arxiv.org/abs/1906.02174v3","paper_title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","code":"https://github.com/PwnerHarry/Stronger_GCN","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"SuperGAT MX","metrics":{"Accuracy":"81.7%"},"uses_additional_data":false,"paper_date":"2022-04-11","paper":"/paper/how-to-find-your-friendly-neighborhood-graph-1","paper_url":"https://arxiv.org/abs/2204.04879v1","paper_title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/conv/supergat_conv.py","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"GCN","metrics":{"Accuracy":"81.12 ± 0.52"},"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":9,"model":"GraphMix (GCN)","metrics":{"Accuracy":"80.98 ± 0.55"},"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":10,"model":"G-APPNP","metrics":{"Accuracy":"80.95%"},"uses_additional_data":false,"paper_date":"2019-10-27","paper":"/paper/pre-train-and-learn-preserve-global","paper_url":"https://arxiv.org/abs/1910.12241v2","paper_title":"Pre-train and Learn: Preserve Global Information for Graph Neural Networks","code":"https://github.com/zhudanhao/g-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"GGCM","metrics":{"Accuracy":"80.8%"},"uses_additional_data":false,"paper_date":"2023-09-24","paper":"/paper/from-cluster-assumption-to-graph-convolution","paper_url":"https://arxiv.org/abs/2309.13599v2","paper_title":"From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited","code":"https://github.com/zhengwang100/ogc_ggcm","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"DAGNN (Ours)","metrics":{"Accuracy":"80.5 ± 0.5"},"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":13,"model":"GCN(predicted-targets)","metrics":{"Accuracy":"80.42%"},"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":14,"model":"SSGC","metrics":{"Accuracy":"80.4"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/simple-spectral-graph-convolution","paper_url":"https://openreview.net/forum?id=CYO5T-YjWZV","paper_title":"Simple Spectral Graph Convolution","code":"https://github.com/allenhaozhu/SSGC","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"GCNII","metrics":{"Accuracy":"80.2%"},"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":16,"model":"SSP","metrics":{"Accuracy":"80.06 ± 0.34%"},"uses_additional_data":false,"paper_date":"2020-08-21","paper":"/paper/optimization-of-graph-neural-networks-with","paper_url":"https://arxiv.org/abs/2008.09624v1","paper_title":"Optimization of Graph Neural Networks with Natural Gradient Descent","code":"https://github.com/russellizadi/ssp","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"AIR-GCN","metrics":{"Accuracy":"80%"},"uses_additional_data":false,"paper_date":"2019-11-05","paper":"/paper/graphair-graph-representation-learning-with","paper_url":"https://arxiv.org/abs/1911.01731v3","paper_title":"GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction","code":"https://github.com/CRIPAC-DIG/GraphAIR","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Graph-MLP","metrics":{"Accuracy":"79.91"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/graph-entropy-minimization-for-semi","paper_url":"https://arxiv.org/abs/2305.19502v1","paper_title":"Graph Entropy Minimization for Semi-supervised Node Classification","code":"https://github.com/cf020031308/gem","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"H-GCN","metrics":{"Accuracy":"79.8%"},"uses_additional_data":false,"paper_date":"2019-02-13","paper":"/paper/semi-supervised-node-classification-via","paper_url":"https://arxiv.org/abs/1902.06667v4","paper_title":"Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification","code":"https://github.com/CRIPAC-DIG/H-GCN","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":5,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"GCN+DropEdge","metrics":{"Accuracy":"79.60%"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"Snowball (tanh)","metrics":{"Accuracy":"79.16%"},"uses_additional_data":false,"paper_date":"2019-06-05","paper":"/paper/break-the-ceiling-stronger-multi-scale-deep","paper_url":"https://arxiv.org/abs/1906.02174v3","paper_title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","code":"https://github.com/PwnerHarry/Stronger_GCN","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"Snowball (linear)","metrics":{"Accuracy":"79.10%"},"uses_additional_data":false,"paper_date":"2019-06-05","paper":"/paper/break-the-ceiling-stronger-multi-scale-deep","paper_url":"https://arxiv.org/abs/1906.02174v3","paper_title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","code":"https://github.com/PwnerHarry/Stronger_GCN","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"GAT","metrics":{"Accuracy":"79.0%"},"uses_additional_data":false,"paper_date":"2017-10-30","paper":"/paper/graph-attention-networks","paper_url":"http://arxiv.org/abs/1710.10903v3","paper_title":"Graph Attention Networks","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":93,"syntology":{"n_ran":50,"n_unverified":56,"n_samples":106,"n_pointer_only_licence":43}},{"rank_in_archive_order":24,"model":"SEGCN","metrics":{"Accuracy":"78.9 ± 0.7"},"uses_additional_data":false,"paper_date":"2018-09-26","paper":"/paper/every-node-counts-self-ensembling-graph","paper_url":"http://arxiv.org/abs/1809.09925v1","paper_title":"Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning","code":"https://github.com/RoyalVane/SEGCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"GEM","metrics":{"Accuracy":"78.48"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/graph-entropy-minimization-for-semi","paper_url":"https://arxiv.org/abs/2305.19502v1","paper_title":"Graph Entropy Minimization for Semi-supervised Node Classification","code":"https://github.com/cf020031308/gem","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"G3NN","metrics":{"Accuracy":"78.4%"},"uses_additional_data":false,"paper_date":"2019-05-26","paper":"/paper/a-flexible-generative-framework-for-graph","paper_url":"https://arxiv.org/abs/1905.10769v2","paper_title":"A Flexible Generative Framework for Graph-based Semi-supervised Learning","code":"https://github.com/jiaqima/G3NN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"LanczosNet","metrics":{"Accuracy":"78.3 ± 0.3"},"uses_additional_data":false,"paper_date":"2019-01-06","paper":"/paper/lanczosnet-multi-scale-deep-graph","paper_url":"https://arxiv.org/abs/1901.01484v2","paper_title":"LanczosNet: Multi-Scale Deep Graph Convolutional Networks","code":"https://github.com/lrjconan/LanczosNetwork","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"AdaLanczosNet","metrics":{"Accuracy":"78.1 ± 0.4"},"uses_additional_data":false,"paper_date":"2019-01-06","paper":"/paper/lanczosnet-multi-scale-deep-graph","paper_url":"https://arxiv.org/abs/1901.01484v2","paper_title":"LanczosNet: Multi-Scale Deep Graph Convolutional Networks","code":"https://github.com/lrjconan/LanczosNetwork","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"DCNN","metrics":{"Accuracy":"76.8%"},"uses_additional_data":false,"paper_date":"2015-11-06","paper":"/paper/diffusion-convolutional-neural-networks","paper_url":"http://arxiv.org/abs/1511.02136v6","paper_title":"Diffusion-Convolutional Neural Networks","code":"https://github.com/jcatw/dcnn","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"GraphSAGE","metrics":{"Accuracy":"76.8%"},"uses_additional_data":false,"paper_date":"2017-06-07","paper":"/paper/inductive-representation-learning-on-large","paper_url":"http://arxiv.org/abs/1706.02216v4","paper_title":"Inductive Representation Learning on Large Graphs","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/models/basic_gnn.py","n_code_links":20,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":31,"model":"GCN-FP","metrics":{"Accuracy":"76.0%"},"uses_additional_data":false,"paper_date":"2015-09-30","paper":"/paper/convolutional-networks-on-graphs-for-learning","paper_url":"http://arxiv.org/abs/1509.09292v2","paper_title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","code":"https://github.com/HIPS/neural-fingerprint","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":26,"n_samples":26,"n_pointer_only_licence":1}},{"rank_in_archive_order":32,"model":"GGNN","metrics":{"Accuracy":"75.8%"},"uses_additional_data":false,"paper_date":"2015-11-17","paper":"/paper/gated-graph-sequence-neural-networks","paper_url":"http://arxiv.org/abs/1511.05493v4","paper_title":"Gated Graph Sequence Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/ggnn","n_code_links":13,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"CoLinkDist","metrics":{"Accuracy":"75.64%"},"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":34,"model":"CoLinkDistMLP","metrics":{"Accuracy":"75.41%"},"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":35,"model":"LinkDist","metrics":{"Accuracy":"74.06%"},"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":36,"model":"LinkDistMLP","metrics":{"Accuracy":"72.41%"},"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":37,"model":"ChebyNet","metrics":{"Accuracy":"69.8%"},"uses_additional_data":false,"paper_date":"2016-06-30","paper":"/paper/convolutional-neural-networks-on-graphs-with","paper_url":"http://arxiv.org/abs/1606.09375v3","paper_title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","code":"https://github.com/mdeff/cnn_graph","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":2}}],"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":22,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":92,"n_unverified":146,"n_samples":238,"n_pointer_only_licence":63,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":94,"n_unverified":165,"n_samples":259,"n_pointer_only_licence":66,"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"}}}