{"url":"/sota/graph-classification-on-imdb-m","task":{"name":"Graph Classification","url":"/task/graph-classification","note":null},"dataset":{"name":"IMDb-M","url":"/dataset/imdb-multi"},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":"**Graph Classification** is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Hierarchical Graph Pooling with Structure Learning](https://github.com/cszhangzhen/HGP-SL) )</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","Accuracy (10-fold)"],"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","Accuracy (10-fold)":"higher"}},"counts":{"rows":36,"rows_with_code":33,"rows_with_paper_page":36,"rows_dated":36,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"U2GNN (Unsupervised)","metrics":{"Accuracy":"89.2%"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/unsupervised-universal-self-attention-network","paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","code":"https://github.com/daiquocnguyen/Graph-Transformer","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"TFGW ADJ (L=2)","metrics":{"Accuracy":"56.8%"},"uses_additional_data":false,"paper_date":"2022-05-31","paper":"/paper/template-based-graph-neural-network-with","paper_url":"https://arxiv.org/abs/2205.15733v1","paper_title":"Template based Graph Neural Network with Optimal Transport Distances","code":"https://github.com/cedricvincentcuaz/TFGW","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"TREE-G","metrics":{"Accuracy":"56.4%"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/graph-trees-with-attention","paper_url":"https://arxiv.org/abs/2207.02760v5","paper_title":"TREE-G: Decision Trees Contesting Graph Neural Networks","code":"https://github.com/mayabechlerspeicher/tree-g","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MEWISPool","metrics":{"Accuracy":"56.23%"},"uses_additional_data":false,"paper_date":"2021-07-03","paper":"/paper/maximum-entropy-weighted-independent-set","paper_url":"https://arxiv.org/abs/2107.01410v1","paper_title":"Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks","code":"https://github.com/mewispool/mewispool","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"DUGNN","metrics":{"Accuracy":"56.10%"},"uses_additional_data":true,"paper_date":"2019-09-22","paper":"/paper/190910086","paper_url":"https://arxiv.org/abs/1909.10086v3","paper_title":"Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning","code":"https://github.com/vermaMachineLearning/Universal-Graph-Embedding-Neural-Network","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"G_ResNet","metrics":{"Accuracy":"54.53%"},"uses_additional_data":false,"paper_date":"2018-07-07","paper":"/paper/when-work-matters-transforming-classical","paper_url":"http://arxiv.org/abs/1807.02653v1","paper_title":"When Work Matters: Transforming Classical Network Structures to Graph CNN","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"sGIN","metrics":{"Accuracy":"54.52%"},"uses_additional_data":false,"paper_date":"2019-05-21","paper":"/paper/neighborhood-enlargement-in-graph-neural","paper_url":"https://arxiv.org/abs/1905.08509v4","paper_title":"Mutual Information Maximization in Graph Neural Networks","code":"https://github.com/CODE-SUBMIT/Graph_Neighborhood_1","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"GIUNet","metrics":{"Accuracy":"54%"},"uses_additional_data":false,"paper_date":"2023-08-23","paper":"/paper/graph-isomorphism-unet","paper_url":"https://www.sciencedirect.com/science/article/abs/pii/S0957417423017827#preview-section-abstract","paper_title":"Graph isomorphism UNet","code":"https://github.com/aramiracle/GIUNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"U2GNN","metrics":{"Accuracy":"53.60%"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/unsupervised-universal-self-attention-network","paper_url":"https://arxiv.org/abs/1909.11855v9","paper_title":"Universal Graph Transformer Self-Attention Networks","code":"https://github.com/daiquocnguyen/Graph-Transformer","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"SEG-BERT","metrics":{"Accuracy":"53.4%"},"uses_additional_data":false,"paper_date":"2020-02-09","paper":"/paper/segmented-graph-bert-for-graph-instance","paper_url":"https://arxiv.org/abs/2002.03283v1","paper_title":"Segmented Graph-Bert for Graph Instance Modeling","code":"https://github.com/jwzhanggy/SEG-BERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"GIN-0","metrics":{"Accuracy":"52.3%"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/how-powerful-are-graph-neural-networks","paper_url":"http://arxiv.org/abs/1810.00826v3","paper_title":"How Powerful are Graph Neural Networks?","code":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gin","n_code_links":19,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":5}},{"rank_in_archive_order":12,"model":"WEGL","metrics":{"Accuracy":"52%"},"uses_additional_data":false,"paper_date":"2020-06-16","paper":"/paper/wasserstein-embedding-for-graph-learning","paper_url":"https://arxiv.org/abs/2006.09430v2","paper_title":"Wasserstein Embedding for Graph Learning","code":"https://github.com/navid-naderi/WEGL","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"GFN","metrics":{"Accuracy":"51.80%"},"uses_additional_data":false,"paper_date":"2019-05-11","paper":"/paper/dissecting-graph-neural-networks-on-graph","paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","code":"https://github.com/chentingpc/gfn","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"1-WL Kernel","metrics":{"Accuracy":"51.5%"},"uses_additional_data":false,"paper_date":"2018-10-04","paper":"/paper/weisfeiler-and-leman-go-neural-higher-order","paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","code":"https://github.com/chrsmrrs/k-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"DropGIN","metrics":{"Accuracy":"51.4%"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/dropgnn-random-dropouts-increase-the","paper_url":"https://arxiv.org/abs/2111.06283v1","paper_title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","code":"https://github.com/karolismart/dropgnn","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"GFN-light","metrics":{"Accuracy":"51.20%"},"uses_additional_data":false,"paper_date":"2019-05-11","paper":"/paper/dissecting-graph-neural-networks-on-graph","paper_url":"https://arxiv.org/abs/1905.04579v3","paper_title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","code":"https://github.com/chentingpc/gfn","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"UGraphEmb-F","metrics":{"Accuracy":"50.97%"},"uses_additional_data":false,"paper_date":"2019-04-01","paper":"/paper/unsupervised-inductive-whole-graph-embedding","paper_url":"https://arxiv.org/abs/1904.01098v2","paper_title":"Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity","code":"https://github.com/yunshengb/UGraphEmb","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"Graph-JEPA","metrics":{"Accuracy":"50.69%"},"uses_additional_data":false,"paper_date":"2023-09-27","paper":"/paper/graph-level-representation-learning-with","paper_url":"https://arxiv.org/abs/2309.16014v3","paper_title":"Graph-level Representation Learning with Joint-Embedding Predictive Architectures","code":"https://github.com/geriskenderi/graph-jepa","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"GMT","metrics":{"Accuracy":"50.66%"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/accurate-learning-of-graph-representations-1","paper_url":"https://arxiv.org/abs/2102.11533v4","paper_title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","code":"https://github.com/JinheonBaek/GMT","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":20,"model":"GDL","metrics":{"Accuracy":"50.64%"},"uses_additional_data":false,"paper_date":"2021-02-12","paper":"/paper/online-graph-dictionary-learning","paper_url":"https://arxiv.org/abs/2102.06555v2","paper_title":"Online Graph Dictionary Learning","code":"https://github.com/cedricvincentcuaz/GDL","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"δ-2-LWL","metrics":{"Accuracy":"50.5%"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/towards-a-practical-k-dimensional-weisfeiler","paper_url":"https://arxiv.org/abs/1904.01543v3","paper_title":"Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings","code":"https://github.com/chrsmrrs/sparsewl","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"CapsGNN","metrics":{"Accuracy":"50.27%"},"uses_additional_data":false,"paper_date":"2019-05-01","paper":"/paper/capsule-graph-neural-network","paper_url":"https://openreview.net/forum?id=Byl8BnRcYm","paper_title":"Capsule Graph Neural Network","code":"https://github.com/benedekrozemberczki/CapsGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"UGraphEmb","metrics":{"Accuracy":"50.06%"},"uses_additional_data":false,"paper_date":"2019-04-01","paper":"/paper/unsupervised-inductive-whole-graph-embedding","paper_url":"https://arxiv.org/abs/1904.01098v2","paper_title":"Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity","code":"https://github.com/yunshengb/UGraphEmb","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"Local Topological Profile (LTP)","metrics":{"Accuracy":"50.0 ± 4.6","Accuracy (10-fold)":"50.0 ± 4.6"},"uses_additional_data":false,"paper_date":"2023-05-01","paper":"/paper/strengthening-structural-baselines-for-graph","paper_url":"https://arxiv.org/abs/2305.00724v1","paper_title":"Strengthening structural baselines for graph classification using Local Topological Profile","code":"https://github.com/j-adamczyk/ltp","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"PPGN","metrics":{"Accuracy":"50%"},"uses_additional_data":false,"paper_date":"2019-05-27","paper":"/paper/provably-powerful-graph-networks","paper_url":"https://arxiv.org/abs/1905.11136v4","paper_title":"Provably Powerful Graph Networks","code":"https://github.com/hadarser/ProvablyPowerfulGraphNetworks_torch","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"InfoGraph","metrics":{"Accuracy":"49.69%"},"uses_additional_data":false,"paper_date":"2019-07-31","paper":"/paper/infograph-unsupervised-and-semi-supervised","paper_url":"https://arxiv.org/abs/1908.01000v3","paper_title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/infograph","n_code_links":5,"syntology":null},{"rank_in_archive_order":27,"model":"k-GNN","metrics":{"Accuracy":"49.5%"},"uses_additional_data":false,"paper_date":"2018-10-04","paper":"/paper/weisfeiler-and-leman-go-neural-higher-order","paper_url":"https://arxiv.org/abs/1810.02244v5","paper_title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","code":"https://github.com/chrsmrrs/k-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"WKPI-kcenters","metrics":{"Accuracy":"49.5%"},"uses_additional_data":false,"paper_date":"2019-04-27","paper":"/paper/learning-metrics-for-persistence-based-2","paper_url":"https://arxiv.org/abs/1904.12189v2","paper_title":"Learning metrics for persistence-based summaries and applications for graph classification","code":"https://github.com/topology474/WKPI","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"hGANet","metrics":{"Accuracy":"49.06%"},"uses_additional_data":false,"paper_date":"2019-07-05","paper":"/paper/graph-representation-learning-via-hard-and","paper_url":"https://arxiv.org/abs/1907.04652v1","paper_title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hardgat","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"ApproxRepSet","metrics":{"Accuracy":"48.92%"},"uses_additional_data":false,"paper_date":"2019-04-03","paper":"/paper/rep-the-set-neural-networks-for-learning-set","paper_url":"https://arxiv.org/abs/1904.01962v2","paper_title":"Rep the Set: Neural Networks for Learning Set Representations","code":"https://github.com/giannisnik/repset","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"DGCNN","metrics":{"Accuracy":"47.83%"},"uses_additional_data":false,"paper_date":"2018-04-29","paper":"/paper/an-end-to-end-deep-learning-architecture-for","paper_url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","paper_title":"An End-to-End Deep Learning Architecture for Graph Classification","code":"https://github.com/muhanzhang/DGCNN","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"GraphSAGE","metrics":{"Accuracy":"47.6%"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/a-fair-comparison-of-graph-neural-networks-1","paper_url":"https://arxiv.org/abs/1912.09893v3","paper_title":"A Fair Comparison of Graph Neural Networks for Graph Classification","code":"https://github.com/diningphil/gnn-comparison","n_code_links":5,"syntology":null},{"rank_in_archive_order":33,"model":"DGK","metrics":{"Accuracy":"44.55%"},"uses_additional_data":false,"paper_date":"2015-08-10","paper":"/paper/deep-graph-kernels","paper_url":"https://www.semanticscholar.org/paper/Deep-Graph-Kernels-Yanardag-Vishwanathan/8ccd0adb1a00358ede79f1d9bdcce472dc1cb8d4","paper_title":"Deep Graph Kernels","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"SPI-GCN","metrics":{"Accuracy":"44.13%"},"uses_additional_data":false,"paper_date":"2019-04-08","paper":"/paper/spi-gcn-a-simple-permutation-invariant-graph","paper_url":"https://hal.archives-ouvertes.fr/hal-02093451/","paper_title":"SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"DGCNN (sum)","metrics":{"Accuracy":"42.76%"},"uses_additional_data":false,"paper_date":"2018-04-29","paper":"/paper/an-end-to-end-deep-learning-architecture-for","paper_url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","paper_title":"An End-to-End Deep Learning Architecture for Graph Classification","code":"https://github.com/muhanzhang/DGCNN","n_code_links":2,"syntology":null},{"rank_in_archive_order":36,"model":"G-Tuning","metrics":{"Accuracy (10-fold)":"51.80"},"uses_additional_data":false,"paper_date":"2023-12-21","paper":"/paper/fine-tuning-graph-neural-networks-by","paper_url":"https://arxiv.org/abs/2312.13583v1","paper_title":"Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns","code":"https://github.com/zjunet/G-Tuning","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":0,"n_samples":13,"n_pointer_only_licence":13}}],"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":11,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":36,"n_unverified":31,"n_samples":67,"n_pointer_only_licence":26,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":40,"n_unverified":31,"n_samples":71,"n_pointer_only_licence":26,"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"}}}