{"url":"/sota/graph-classification-on-nci109","task":{"name":"Graph Classification","url":"/task/graph-classification","note":null},"dataset":{"name":"NCI109","url":"/dataset/nci109"},"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":38,"rows_with_code":31,"rows_with_paper_page":38,"rows_dated":38,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"WKPI-kcenters","metrics":{"Accuracy":"87.3"},"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":2,"model":"WL-OA","metrics":{"Accuracy":"86.3"},"uses_additional_data":false,"paper_date":"2016-06-03","paper":"/paper/on-valid-optimal-assignment-kernels-and","paper_url":"http://arxiv.org/abs/1606.01141v3","paper_title":"On Valid Optimal Assignment Kernels and Applications to Graph Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"ESA (Edge set attention, no positional encodings)","metrics":{"Accuracy":"84.976±0.551"},"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":4,"model":"δ-2-LWL","metrics":{"Accuracy":"84.7"},"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":5,"model":"CIN++","metrics":{"Accuracy":"84.5"},"uses_additional_data":false,"paper_date":"2023-06-06","paper":"/paper/cin-enhancing-topological-message-passing","paper_url":"https://arxiv.org/abs/2306.03561v1","paper_title":"CIN++: Enhancing Topological Message Passing","code":"https://github.com/twitter-research/cwn","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"GIN","metrics":{"Accuracy":"84.155±0.812"},"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":7,"model":"PIN","metrics":{"Accuracy":"84.0"},"uses_additional_data":false,"paper_date":"2023-08-13","paper":"/paper/generalizing-topological-graph-neural","paper_url":"https://arxiv.org/abs/2308.06838v6","paper_title":"Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"DropGIN","metrics":{"Accuracy":"83.961±1.141"},"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":9,"model":"Spec-GN","metrics":{"Accuracy":"83.62"},"uses_additional_data":false,"paper_date":"2021-12-14","paper":"/paper/improving-spectral-graph-convolution-for","paper_url":"https://arxiv.org/abs/2112.07160v2","paper_title":"A New Perspective on the Effects of Spectrum in Graph Neural Networks","code":"https://github.com/qslim/gnn-spectrum","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"CAN","metrics":{"Accuracy":"83.6"},"uses_additional_data":false,"paper_date":"2022-09-16","paper":"/paper/cell-attention-networks","paper_url":"https://arxiv.org/abs/2209.08179v1","paper_title":"Cell Attention Networks","code":"https://github.com/lrnzgiusti/can","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Propagation kernels (pk)","metrics":{"Accuracy":"83.5"},"uses_additional_data":false,"paper_date":"2019-02-01","paper":"/paper/propagation-kernels-efficient-graph-kernels","paper_url":"https://doi.org/10.1007/s10994-015-5517-9","paper_title":"Propagation kernels: efficient graph kernels from propagated information","code":"https://github.com/marionmari/propagation_kernels","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"PNA","metrics":{"Accuracy":"83.382±1.045"},"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":"GCN","metrics":{"Accuracy":"83.140±1.248"},"uses_additional_data":false,"paper_date":"2016-09-09","paper":"/paper/semi-supervised-classification-with-graph","paper_url":"http://arxiv.org/abs/1609.02907v4","paper_title":"Semi-Supervised Classification with Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gcn","n_code_links":55,"syntology":{"n_ran":31,"n_unverified":27,"n_samples":58,"n_pointer_only_licence":22}},{"rank_in_archive_order":14,"model":"GATv2","metrics":{"Accuracy":"83.092±0.764"},"uses_additional_data":false,"paper_date":"2021-05-30","paper":"/paper/how-attentive-are-graph-attention-networks","paper_url":"https://arxiv.org/abs/2105.14491v3","paper_title":"How Attentive are Graph Attention Networks?","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":8,"syntology":{"n_ran":6,"n_unverified":10,"n_samples":16,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"GIC","metrics":{"Accuracy":"82.86"},"uses_additional_data":false,"paper_date":"2018-11-11","paper":"/paper/gaussian-induced-convolution-for-graphs","paper_url":"http://arxiv.org/abs/1811.04393v1","paper_title":"Gaussian-Induced Convolution for Graphs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"GAT","metrics":{"Accuracy":"82.560±0.601"},"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":17,"model":"PPGN","metrics":{"Accuracy":"82.23"},"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":18,"model":"ECC (5 scores)","metrics":{"Accuracy":"82.14"},"uses_additional_data":false,"paper_date":"2017-04-10","paper":"/paper/dynamic-edge-conditioned-filters-in","paper_url":"http://arxiv.org/abs/1704.02901v3","paper_title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","code":"https://github.com/rusty1s/pytorch_cluster","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Multigraph ChebNet","metrics":{"Accuracy":"82.0"},"uses_additional_data":false,"paper_date":"2018-11-23","paper":"/paper/spectral-multigraph-networks-for-discovering","paper_url":"http://arxiv.org/abs/1811.09595v1","paper_title":"Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules","code":"https://github.com/bknyaz/graph_nn","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"GraphGPS","metrics":{"Accuracy":"81.256±0.501"},"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":21,"model":"HGP-SL","metrics":{"Accuracy":"80.67"},"uses_additional_data":false,"paper_date":"2019-11-14","paper":"/paper/hierarchical-graph-pooling-with-structure","paper_url":"https://arxiv.org/abs/1911.05954v3","paper_title":"Hierarchical Graph Pooling with Structure Learning","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hgp_sl","n_code_links":3,"syntology":null},{"rank_in_archive_order":22,"model":"G_DenseNet","metrics":{"Accuracy":"80.66"},"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":23,"model":"S-CGIB","metrics":{"Accuracy":"77.54±1.51"},"uses_additional_data":false,"paper_date":"2025-02-20","paper":"/paper/pre-training-graph-neural-networks-on","paper_url":"https://arxiv.org/abs/2412.15589","paper_title":"Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck","code":"https://github.com/NSLab-CUK/S-CGIB","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"GIUNet","metrics":{"Accuracy":"77"},"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":25,"model":"SAEPool_h","metrics":{"Accuracy":"75.85"},"uses_additional_data":false,"paper_date":"2022-04-06","paper":"/paper/relational-reasoning-over-spatial-temporal","paper_url":"https://ieeexplore.ieee.org/abstract/document/9750933","paper_title":"Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"UGT","metrics":{"Accuracy":"75.45±1.26"},"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":27,"model":"EigenGCN-3","metrics":{"Accuracy":"74.90"},"uses_additional_data":false,"paper_date":"2019-04-30","paper":"/paper/graph-convolutional-networks-with","paper_url":"https://arxiv.org/abs/1904.13107v2","paper_title":"Graph Convolutional Networks with EigenPooling","code":"https://github.com/alge24/eigenpooling","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"Graphormer","metrics":{"Accuracy":"74.879±1.183"},"uses_additional_data":false,"paper_date":"2021-06-09","paper":"/paper/do-transformers-really-perform-bad-for-graph","paper_url":"https://arxiv.org/abs/2106.05234v5","paper_title":"Do Transformers Really Perform Bad for Graph Representation?","code":"https://github.com/microsoft/Graphormer","n_code_links":5,"syntology":null},{"rank_in_archive_order":29,"model":"UGraphEmb-F","metrics":{"Accuracy":"74.48"},"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":30,"model":"Graph2Vec","metrics":{"Accuracy":"74.26"},"uses_additional_data":false,"paper_date":"2017-07-17","paper":"/paper/graph2vec-learning-distributed","paper_url":"http://arxiv.org/abs/1707.05005v1","paper_title":"graph2vec: Learning Distributed Representations of Graphs","code":"https://github.com/benedekrozemberczki/karateclub","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":31,"model":"SAGPool_g","metrics":{"Accuracy":"74.06"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/self-attention-graph-pooling","paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool","n_code_links":3,"syntology":null},{"rank_in_archive_order":32,"model":"MAGPool","metrics":{"Accuracy":"73.43%"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/multi-hop-attention-based-graph-pooling-a","paper_url":"https://ieeexplore.ieee.org/document/10454077","paper_title":"Multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective","code":"https://github.com/p-haddadian/MAGPool","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"TokenGT","metrics":{"Accuracy":"72.077±1.883"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/pure-transformers-are-powerful-graph-learners","paper_url":"https://arxiv.org/abs/2207.02505v2","paper_title":"Pure Transformers are Powerful Graph Learners","code":"https://github.com/jw9730/tokengt","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":34,"model":"Deep WL SGN(0,1,2)","metrics":{"Accuracy":"71.06"},"uses_additional_data":false,"paper_date":"2019-03-21","paper":"/paper/subgraph-networks-with-application-to","paper_url":"https://arxiv.org/abs/1903.09022v3","paper_title":"Subgraph Networks with Application to Structural Feature Space Expansion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"ASAP","metrics":{"Accuracy":"70.07"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/asap-adaptive-structure-aware-pooling-for","paper_url":"https://arxiv.org/abs/1911.07979v3","paper_title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","code":"https://github.com/malllabiisc/ASAP","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"UGraphEmb","metrics":{"Accuracy":"69.17"},"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":37,"model":"SAGPool_h","metrics":{"Accuracy":"67.86"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/self-attention-graph-pooling","paper_url":"https://arxiv.org/abs/1904.08082v4","paper_title":"Self-Attention Graph Pooling","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sagpool","n_code_links":3,"syntology":null},{"rank_in_archive_order":38,"model":"BC + Capsules","metrics":{"Accuracy":"58.04"},"uses_additional_data":false,"paper_date":"2019-02-22","paper":"/paper/capsule-neural-networks-for-graph","paper_url":"http://arxiv.org/abs/1902.08399v1","paper_title":"Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":16,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":16,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":141,"n_unverified":185,"n_samples":326,"n_pointer_only_licence":129,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":141,"n_unverified":185,"n_samples":326,"n_pointer_only_licence":129,"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"}}}