{"url":"/sota/graph-classification-on-cifar10-100k","task":{"name":"Graph Classification","url":"/task/graph-classification","note":null},"dataset":{"name":"CIFAR10 100k","url":"/dataset/cifar-10"},"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 (%)"],"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":20,"rows_with_code":19,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"NeuralWalker","metrics":{"Accuracy (%)":"80.027 ± 0.185"},"uses_additional_data":false,"paper_date":"2024-06-05","paper":"/paper/learning-long-range-dependencies-on-graphs","paper_url":"https://arxiv.org/abs/2406.03386v2","paper_title":"Learning Long Range Dependencies on Graphs via Random Walks","code":"https://github.com/borgwardtlab/neuralwalker","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":0,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"GatedGCN+","metrics":{"Accuracy (%)":"77.218 ± 0.381"},"uses_additional_data":false,"paper_date":"2025-02-13","paper":"/paper/unlocking-the-potential-of-classic-gnns-for","paper_url":"https://arxiv.org/abs/2502.09263v1","paper_title":"Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence","code":"https://github.com/LUOyk1999/GNNPlus","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GRED","metrics":{"Accuracy (%)":"76.853±0.185"},"uses_additional_data":false,"paper_date":"2023-12-03","paper":"/paper/recurrent-distance-encoding-neural-networks","paper_url":"https://arxiv.org/abs/2312.01538v3","paper_title":"Recurrent Distance Filtering for Graph Representation Learning","code":"https://github.com/skeletondyh/gred","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":9,"n_samples":21,"n_pointer_only_licence":21}},{"rank_in_archive_order":4,"model":"GRIT","metrics":{"Accuracy (%)":"76.468"},"uses_additional_data":false,"paper_date":"2023-05-27","paper":"/paper/graph-inductive-biases-in-transformers","paper_url":"https://arxiv.org/abs/2305.17589v1","paper_title":"Graph Inductive Biases in Transformers without Message Passing","code":"https://github.com/liamma/grit","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":6,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"GraphGPS + HDSE","metrics":{"Accuracy (%)":"76.180±0.277"},"uses_additional_data":false,"paper_date":"2023-08-22","paper":"/paper/transformers-for-capturing-multi-level-graph","paper_url":"https://arxiv.org/abs/2308.11129v4","paper_title":"Enhancing Graph Transformers with Hierarchical Distance Structural Encoding","code":"https://github.com/luoyk1999/hdse","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"ESA (Edge set attention, no positional encodings)","metrics":{"Accuracy (%)":"75.413±0.248"},"uses_additional_data":false,"paper_date":"2024-02-16","paper":"/paper/masked-attention-is-all-you-need-for-graphs","paper_url":"https://arxiv.org/abs/2402.10793v2","paper_title":"An end-to-end attention-based approach for learning on graphs","code":"https://github.com/davidbuterez/edge-set-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Exphormer","metrics":{"Accuracy (%)":"74.754±0.194"},"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":8,"model":"TIGT","metrics":{"Accuracy (%)":"73.955"},"uses_additional_data":false,"paper_date":"2024-02-03","paper":"/paper/topology-informed-graph-transformer","paper_url":"https://arxiv.org/abs/2402.02005v1","paper_title":"Topology-Informed Graph Transformer","code":"https://github.com/leemingo/tigt","n_code_links":2,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":21}},{"rank_in_archive_order":9,"model":"ARGNP","metrics":{"Accuracy (%)":"73.90"},"uses_additional_data":false,"paper_date":"2022-05-31","paper":"/paper/automatic-relation-aware-graph-network","paper_url":"https://arxiv.org/abs/2205.15678v1","paper_title":"Automatic Relation-aware Graph Network Proliferation","code":"https://github.com/phython96/ARGNP","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DGN","metrics":{"Accuracy (%)":"72.84"},"uses_additional_data":false,"paper_date":"2020-10-06","paper":"/paper/directional-graph-networks-1","paper_url":"https://arxiv.org/abs/2010.02863v4","paper_title":"Directional Graph Networks","code":"https://github.com/Saro00/DGN","n_code_links":2,"syntology":{"n_ran":12,"n_unverified":2,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GPS","metrics":{"Accuracy (%)":"72.298"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/recipe-for-a-general-powerful-scalable-graph","paper_url":"https://arxiv.org/abs/2205.12454v4","paper_title":"Recipe for a General, Powerful, Scalable Graph Transformer","code":"https://github.com/rampasek/GraphGPS","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":18,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"PNA","metrics":{"Accuracy (%)":"70.47"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/principal-neighbourhood-aggregation-for-graph","paper_url":"https://arxiv.org/abs/2004.05718v5","paper_title":"Principal Neighbourhood Aggregation for Graph Nets","code":"https://github.com/rusty1s/pytorch_geometric","n_code_links":8,"syntology":{"n_ran":33,"n_unverified":22,"n_samples":55,"n_pointer_only_licence":48}},{"rank_in_archive_order":13,"model":"EIGENFORMER","metrics":{"Accuracy (%)":"70.194"},"uses_additional_data":false,"paper_date":"2024-01-31","paper":"/paper/graph-transformers-without-positional","paper_url":"https://arxiv.org/abs/2401.17791v3","paper_title":"Graph Transformers without Positional Encodings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"GatedGCN","metrics":{"Accuracy (%)":"69.37"},"uses_additional_data":false,"paper_date":"2017-11-20","paper":"/paper/residual-gated-graph-convnets","paper_url":"http://arxiv.org/abs/1711.07553v2","paper_title":"Residual Gated Graph ConvNets","code":"https://github.com/xbresson/spatial_graph_convnets","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"EGT","metrics":{"Accuracy (%)":"68.702"},"uses_additional_data":false,"paper_date":"2021-08-07","paper":"/paper/edge-augmented-graph-transformers-global-self","paper_url":"https://arxiv.org/abs/2108.03348v3","paper_title":"Global Self-Attention as a Replacement for Graph Convolution","code":"https://github.com/shamim-hussain/egt_pytorch","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"GatedGCN","metrics":{"Accuracy (%)":"67.312"},"uses_additional_data":false,"paper_date":"2020-03-02","paper":"/paper/benchmarking-graph-neural-networks","paper_url":"https://arxiv.org/abs/2003.00982v5","paper_title":"Benchmarking Graph Neural Networks","code":"https://github.com/graphdeeplearning/benchmarking-gnns","n_code_links":15,"syntology":{"n_ran":8,"n_unverified":15,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"GraphSage","metrics":{"Accuracy (%)":"66.08"},"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":18,"model":"GAT","metrics":{"Accuracy (%)":"65.48"},"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":51,"n_unverified":55,"n_samples":106,"n_pointer_only_licence":43}},{"rank_in_archive_order":19,"model":"MoNet","metrics":{"Accuracy (%)":"53.42"},"uses_additional_data":false,"paper_date":"2016-11-25","paper":"/paper/geometric-deep-learning-on-graphs-and","paper_url":"http://arxiv.org/abs/1611.08402v3","paper_title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","code":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/monet","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"GIN","metrics":{"Accuracy (%)":"53.28"},"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}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":16,"rows_with_any_sample_ran":13,"distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":13,"samples_over_distinct_papers":{"n_ran":163,"n_unverified":161,"n_samples":324,"n_pointer_only_licence":143,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":163,"n_unverified":161,"n_samples":324,"n_pointer_only_licence":143,"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"}}}