{"url":"/sota/graph-property-prediction-on-ogbg-molpcba","task":{"name":"Graph Property Prediction","url":"/task/graph-property-prediction","note":null},"dataset":{"name":"ogbg-molpcba","url":"/dataset/ogb"},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":null,"description_from":null,"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":["Test AP","Ext. data","Validation AP","Number of params"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test AP":"higher","Ext. data":null,"Validation AP":"higher","Number of params":"lower"}},"counts":{"rows":36,"rows_with_code":29,"rows_with_paper_page":30,"rows_dated":30,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"HyperFusino","metrics":{"Ext. data":"No","Number of params":"10887085","Test AP":"0.3204 ± 0.0001","Validation AP":"0.3353 ± 0.0002"},"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":2,"model":"HyperFusion","metrics":{"Ext. data":"No","Number of params":"10887085","Test AP":"0.3204 ± 0.0001","Validation AP":"0.3353 ± 0.0002"},"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":3,"model":"HIG(pre-trained on PCQM4M)","metrics":{"Ext. data":"Yes","Number of params":"119529665","Test AP":"0.3167 ± 0.0034","Validation AP":"0.3252 ± 0.0043"},"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":4,"model":"TGT-Ag+TGT-At-DP","metrics":{"Ext. data":"Yes","Number of params":"47000000","Test AP":"0.3167 ± 0.0031"},"uses_additional_data":true,"paper_date":"2024-02-07","paper":"/paper/triplet-interaction-improves-graph","paper_url":"https://arxiv.org/abs/2402.04538v2","paper_title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","code":"https://github.com/shamim-hussain/egt_pytorch","n_code_links":3,"syntology":{"n_ran":10,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Graphormer","metrics":{"Number of params":"119529664","Test AP":"0.3140 ± 0.0032","Validation AP":"0.3227 ± 0.0024"},"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":6,"model":"Graphormer (pre-trained on PCQM4M)","metrics":{"Ext. data":"Yes","Number of params":"119529664","Test AP":"0.3140 ± 0.0032","Validation AP":"0.3227 ± 0.0024"},"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":7,"model":"GatedGCN-HSG","metrics":{"Test AP":"0.3129±0.0020"},"uses_additional_data":false,"paper_date":"2024-06-22","paper":"/paper/next-level-message-passing-with-hierarchical","paper_url":"https://arxiv.org/abs/2406.15852v2","paper_title":"Next Level Message-Passing with Hierarchical Support Graphs","code":"https://github.com/carlosinator/support-graphs","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"PDF","metrics":{"Ext. data":"No","Number of params":"3842048","Test AP":"0.3031 ± 0.0026","Validation AP":"0.3115 ± 0.0020"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/towards-better-graph-representation-learning","paper_url":"https://arxiv.org/abs/2305.06102v1","paper_title":"Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering","code":"https://github.com/qslim/PDF","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"PAS","metrics":{"Ext. data":"No","Number of params":"5560960","Test AP":"0.3012 ± 0.0039","Validation AP":"0.3151 ± 0.0047"},"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":10,"model":"Nested GIN+virtual node (ensemble)","metrics":{"Ext. data":"No","Number of params":"44187480","Test AP":"0.3007 ± 0.0037","Validation AP":"0.3059 ± 0.0056"},"uses_additional_data":false,"paper_date":"2021-10-25","paper":"/paper/nested-graph-neural-networks","paper_url":"https://arxiv.org/abs/2110.13197v1","paper_title":"Nested Graph Neural Networks","code":"https://github.com/muhanzhang/NestedGNN","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Nested GIN+virtual node (ens)","metrics":{"Test AP":"0.3007 ± 0.0037","Validation AP":"0.3059 ± 0.0056"},"uses_additional_data":false,"paper_date":"2021-10-25","paper":"/paper/nested-graph-neural-networks","paper_url":"https://arxiv.org/abs/2110.13197v1","paper_title":"Nested Graph Neural Networks","code":"https://github.com/muhanzhang/NestedGNN","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"GINE+bot","metrics":{"Ext. data":"No","Number of params":"5511680","Test AP":"0.2994 ± 0.0019","Validation AP":"0.3094 ± 0.0023"},"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":13,"model":"CRaWl","metrics":{"Ext. data":"No","Number of params":"6115728","Test AP":"0.2986 ± 0.0025","Validation AP":"0.3075 ± 0.0020"},"uses_additional_data":false,"paper_date":"2021-02-17","paper":"/paper/graph-learning-with-1d-convolutions-on-random","paper_url":"https://arxiv.org/abs/2102.08786v3","paper_title":"Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing","code":"https://github.com/toenshoff/CRaWl","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"GatedGCN+","metrics":{"Ext. data":"No","Number of params":"6016860","Test AP":"0.2981 ± 0.0024","Validation AP":"0.3011 ± 0.0037"},"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":15,"model":"GINE+ w/ APPNP","metrics":{"Ext. data":"No","Number of params":"6147029","Test AP":"0.2979 ± 0.0030","Validation AP":"0.3126 ± 0.0023"},"uses_additional_data":false,"paper_date":"2020-11-30","paper":"/paper/graph-convolutions-that-can-finally-model","paper_url":"https://arxiv.org/abs/2011.15069v2","paper_title":"Graph convolutions that can finally model local structure","code":"https://github.com/RBrossard/GINEPLUS","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"EGT","metrics":{"Test AP":"0.2961 ± 0.0024"},"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":17,"model":"PHC-GNN","metrics":{"Ext. data":"No","Number of params":"1690328","Test AP":"0.2947 ± 0.0026","Validation AP":"0.3068 ± 0.0025"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/parameterized-hypercomplex-graph-neural","paper_url":"https://arxiv.org/abs/2103.16584v1","paper_title":"Parameterized Hypercomplex Graph Neural Networks for Graph Classification","code":"https://github.com/bayer-science-for-a-better-life/phc-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"GIN-AK","metrics":{"Ext. data":"No","Number of params":"3081029","Test AP":"0.2930 ± 0.0044","Validation AP":"0.3047 ± 0.0007"},"uses_additional_data":false,"paper_date":"2021-10-07","paper":"/paper/from-stars-to-subgraphs-uplifting-any-gnn","paper_url":"https://arxiv.org/abs/2110.03753v3","paper_title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","code":"https://github.com/GNNAsKernel/GNNAsKernel","n_code_links":2,"syntology":{"n_ran":15,"n_unverified":3,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"GINE+ w/ virtual nodes","metrics":{"Ext. data":"No","Number of params":"6147029","Test AP":"0.2917 ± 0.0015","Validation AP":"0.3065 ± 0.0030"},"uses_additional_data":false,"paper_date":"2020-11-30","paper":"/paper/graph-convolutions-that-can-finally-model","paper_url":"https://arxiv.org/abs/2011.15069v2","paper_title":"Graph convolutions that can finally model local structure","code":"https://github.com/RBrossard/GINEPLUS","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"GPS","metrics":{"Ext. data":"No","Number of params":"9744496","Test AP":"0.2907","Validation AP":"0.3015 ± 0.0038"},"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":"DGN","metrics":{"Ext. data":"No","Number of params":"6732696","Test AP":"0.2885 ± 0.0030","Validation AP":"0.2970 ± 0.0021"},"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":22,"model":"RandomGIN-vn+FLAG","metrics":{"Ext. data":"No","Number of params":"5572026","Test AP":"0.2881 ± 0.0028","Validation AP":"0.3035 ± 0.0047"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/ran-gnns-breaking-the-capacity-limits-of","paper_url":"https://arxiv.org/abs/2103.15565v1","paper_title":"RAN-GNNs: breaking the capacity limits of graph neural networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"DeeperGCN+virtual node+FLAG","metrics":{"Ext. data":"No","Number of params":"5550208","Test AP":"0.2842 ± 0.0043","Validation AP":"0.2952 ± 0.0029"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/flag-adversarial-data-augmentation-for-graph-1","paper_url":"https://arxiv.org/abs/2010.09891v3","paper_title":"Robust Optimization as Data Augmentation for Large-scale Graphs","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"PNA","metrics":{"Ext. data":"No","Number of params":"6550839","Test AP":"0.2838 ± 0.0035","Validation AP":"0.2926 ± 0.0026"},"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":25,"model":"GIN+virtual node+FLAG","metrics":{"Ext. data":"No","Number of params":"3374533","Test AP":"0.2834 ± 0.0038","Validation AP":"0.2912 ± 0.0026"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/flag-adversarial-data-augmentation-for-graph-1","paper_url":"https://arxiv.org/abs/2010.09891v3","paper_title":"Robust Optimization as Data Augmentation for Large-scale Graphs","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"Nested GIN+virtual node","metrics":{"Test AP":"0.2832 ± 0.0041","Validation AP":"0.2915 ± 0.0035"},"uses_additional_data":false,"paper_date":"2021-10-25","paper":"/paper/nested-graph-neural-networks","paper_url":"https://arxiv.org/abs/2110.13197v1","paper_title":"Nested Graph Neural Networks","code":"https://github.com/muhanzhang/NestedGNN","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"DeeperGCN+virtual node","metrics":{"Ext. data":"No","Number of params":"5550208","Test AP":"0.2781 ± 0.0038","Validation AP":"0.2920 ± 0.0025"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/deepergcn-all-you-need-to-train-deeper-gcns","paper_url":"https://arxiv.org/abs/2006.07739v1","paper_title":"DeeperGCN: All You Need to Train Deeper GCNs","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/deepergcn","n_code_links":3,"syntology":null},{"rank_in_archive_order":28,"model":"GIN+virtual node","metrics":{"Ext. data":"No","Number of params":"3374533","Test AP":"0.2703 ± 0.0023","Validation AP":"0.2798 ± 0.0025"},"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":29,"model":"GCN+virtual node+FLAG","metrics":{"Ext. data":"No","Number of params":"2017028","Test AP":"0.2483 ± 0.0037","Validation AP":"0.2556 ± 0.0040"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/flag-adversarial-data-augmentation-for-graph-1","paper_url":"https://arxiv.org/abs/2010.09891v3","paper_title":"Robust Optimization as Data Augmentation for Large-scale Graphs","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"GCN+virtual node","metrics":{"Ext. data":"No","Number of params":"2017028","Test AP":"0.2424 ± 0.0034","Validation AP":"0.2495 ± 0.0042"},"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":32,"n_unverified":26,"n_samples":58,"n_pointer_only_licence":22}},{"rank_in_archive_order":31,"model":"GIN+FLAG","metrics":{"Ext. data":"No","Number of params":"1923433","Test AP":"0.2395 ± 0.0040","Validation AP":"0.2451 ± 0.0042"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/flag-adversarial-data-augmentation-for-graph-1","paper_url":"https://arxiv.org/abs/2010.09891v3","paper_title":"Robust Optimization as Data Augmentation for Large-scale Graphs","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"ChebNet","metrics":{"Ext. data":"No","Number of params":"1475003","Test AP":"0.2306 ± 0.0016","Validation AP":"0.2372 ± 0.0018"},"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}},{"rank_in_archive_order":33,"model":"GIN","metrics":{"Ext. data":"No","Number of params":"1923433","Test AP":"0.2266 ± 0.0028","Validation AP":"0.2305 ± 0.0027"},"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":34,"model":"GCN+FLAG","metrics":{"Ext. data":"No","Number of params":"565928","Test AP":"0.2116 ± 0.0017","Validation AP":"0.2150 ± 0.0022"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/flag-adversarial-data-augmentation-for-graph-1","paper_url":"https://arxiv.org/abs/2010.09891v3","paper_title":"Robust Optimization as Data Augmentation for Large-scale Graphs","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"MorganFP+Rand. Forest","metrics":{"Ext. data":"No","Number of params":"29440000","Test AP":"0.2054 ± 0.0004","Validation AP":"0.2226 ± 0.0002"},"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":36,"model":"GCN","metrics":{"Ext. data":"No","Number of params":"565928","Test AP":"0.2020 ± 0.0024","Validation AP":"0.2059 ± 0.0033"},"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":32,"n_unverified":26,"n_samples":58,"n_pointer_only_licence":22}}],"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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":22,"rows_with_any_sample_ran":20,"distinct_papers_with_graph_line":14,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":122,"n_unverified":120,"n_samples":242,"n_pointer_only_licence":77,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":171,"n_unverified":203,"n_samples":374,"n_pointer_only_licence":104,"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"}}}