{"url":"/sota/node-property-prediction-on-ogbn-products","task":{"name":"Node Property Prediction","url":"/task/node-property-prediction","note":null},"dataset":{"name":"ogbn-products","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 Accuracy","Ext. data","Validation Accuracy","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 Accuracy":"higher","Ext. data":null,"Validation Accuracy":"higher","Number of params":"lower"}},"counts":{"rows":64,"rows_with_code":57,"rows_with_paper_page":57,"rows_dated":57,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GLEM+EnGCN","metrics":{"Ext. data":"Yes","Number of params":"139633805","Test Accuracy":"0.9014 ± 0.0012","Validation Accuracy":"0.9370 ± 0.0004"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/learning-on-large-scale-text-attributed","paper_url":"https://arxiv.org/abs/2210.14709v2","paper_title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","code":"https://github.com/andyjzhao/glem","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"EnGCN","metrics":{"Ext. data":"No","Number of params":"653918","Test Accuracy":"0.8798 ± 0.0004","Validation Accuracy":"0.9241 ± 0.0003"},"uses_additional_data":false,"paper_date":"2022-10-14","paper":"/paper/a-comprehensive-study-on-large-scale-graph","paper_url":"https://arxiv.org/abs/2210.07494v2","paper_title":"A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking","code":"https://github.com/VITA-Group/Large_Scale_GCN_Benchmarking","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"GLEM+GIANT+SAGN+SCR","metrics":{"Ext. data":"Yes","Number of params":"139792525","Test Accuracy":"0.8737 ± 0.0006","Validation Accuracy":"0.9400 ± 0.0003"},"uses_additional_data":false,"paper_date":"2022-10-26","paper":"/paper/learning-on-large-scale-text-attributed","paper_url":"https://arxiv.org/abs/2210.14709v2","paper_title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","code":"https://github.com/andyjzhao/glem","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"LD+GIANT+SAGN+SCR","metrics":{"Ext. data":"Yes","Number of params":"110636896","Test Accuracy":"0.8718 ± 0.0004","Validation Accuracy":"0.9399 ± 0.0002"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/label-deconvolution-for-node-representation","paper_url":"https://arxiv.org/abs/2309.14907v1","paper_title":"Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias","code":"https://github.com/MIRALab-USTC/LD","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"**GraDBERT+GIANT & SAGN+SLE+CnS **","metrics":{"Ext. data":"Yes","Number of params":"1154654","Test Accuracy":"0.8692 ± 0.0007","Validation Accuracy":"0.9371 ± 0.0003"},"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":6,"model":"GIANT-XRT+R-SAGN+SCR+C&S","metrics":{"Ext. data":"Yes","Number of params":"1154142","Test Accuracy":"0.8684 ± 0.0005","Validation Accuracy":"0.9365 ± 0.0003"},"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":7,"model":"GIANT-XRT+SAGN+SCR+C&S","metrics":{"Ext. data":"Yes","Number of params":"1154654","Test Accuracy":"0.8680 ± 0.0007","Validation Accuracy":"0.9357 ± 0.0004"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"GIANT-XRT+SAGN+MCR+C&S","metrics":{"Ext. data":"Yes","Number of params":"1154654","Test Accuracy":"0.8673 ± 0.0008","Validation Accuracy":"0.9387 ± 0.0002"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"GIANT-XRT+SAGN+SCR","metrics":{"Ext. data":"Yes","Number of params":"1154654","Test Accuracy":"0.8667 ± 0.0009","Validation Accuracy":"0.9364 ± 0.0005"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":10,"model":"GIANT-XRT+SAGN+MCR","metrics":{"Ext. data":"Yes","Number of params":"1154654","Test Accuracy":"0.8651 ± 0.0009","Validation Accuracy":"0.9389 ± 0.0002"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"LD+GAMLP","metrics":{"Ext. data":"Yes","Number of params":"144331677","Test Accuracy":"0.8645 ± 0.0012","Validation Accuracy":"0.9415 ± 0.0003"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/label-deconvolution-for-node-representation","paper_url":"https://arxiv.org/abs/2309.14907v1","paper_title":"Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias","code":"https://github.com/MIRALab-USTC/LD","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"GIANT-XRT+SAGN+SLE+C&S (use raw text)","metrics":{"Ext. data":"Yes","Number of params":"1548382","Test Accuracy":"0.8643 ± 0.0020","Validation Accuracy":"0.9352 ± 0.0005"},"uses_additional_data":false,"paper_date":"2021-10-29","paper":"/paper/node-feature-extraction-by-self-supervised-1","paper_url":"https://arxiv.org/abs/2111.00064v3","paper_title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","code":"https://github.com/amzn/pecos","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":14,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"GIANT-XRT+SAGN+SLE (use raw text)","metrics":{"Ext. data":"Yes","Number of params":"1548382","Test Accuracy":"0.8622 ± 0.0022","Validation Accuracy":"0.9363 ± 0.0005"},"uses_additional_data":false,"paper_date":"2021-10-29","paper":"/paper/node-feature-extraction-by-self-supervised-1","paper_url":"https://arxiv.org/abs/2111.00064v3","paper_title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","code":"https://github.com/amzn/pecos","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":14,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"GIANT-XRT+GAMLP+MCR","metrics":{"Ext. data":"Yes","Number of params":"2144151","Test Accuracy":"0.8591 ± 0.0008","Validation Accuracy":"0.9402 ± 0.0004"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"GAMLP+RLU+SCR+C&S","metrics":{"Ext. data":"No","Number of params":"3335831","Test Accuracy":"0.8520 ± 0.0008","Validation Accuracy":"0.9304 ± 0.0005"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"GAMLP+RLU+SCR","metrics":{"Ext. data":"No","Number of params":"3335831","Test Accuracy":"0.8505 ± 0.0009","Validation Accuracy":"0.9292 ± 0.0005"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"SAGN+SLE (4 stages)+C&S","metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8485 ± 0.0010","Validation Accuracy":"0.9302 ± 0.0003"},"uses_additional_data":false,"paper_date":"2021-04-19","paper":"/paper/scalable-and-adaptive-graph-neural-networks","paper_url":"https://arxiv.org/abs/2104.09376v3","paper_title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","code":"https://github.com/skepsun/SAGN_with_SLE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"SAGN+SLE (4 stages)","metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8468 ± 0.0012","Validation Accuracy":"0.9309 ± 0.0007"},"uses_additional_data":false,"paper_date":"2021-04-19","paper":"/paper/scalable-and-adaptive-graph-neural-networks","paper_url":"https://arxiv.org/abs/2104.09376v3","paper_title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","code":"https://github.com/skepsun/SAGN_with_SLE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"GAMLP+MCR","metrics":{"Ext. data":"No","Number of params":"3335831","Test Accuracy":"0.8462 ± 0.0003","Validation Accuracy":"0.9319 ± 0.0003"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"GAMLP+RLU","metrics":{"Ext. data":"No","Number of params":"3335831","Test Accuracy":"0.8459 ± 0.0010","Validation Accuracy":"0.9324 ± 0.0005"},"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":"Spec-MLP-Wide + C&S","metrics":{"Ext. data":"No","Number of params":"406063","Test Accuracy":"0.8451 ± 0.0006","Validation Accuracy":"0.9132 ± 0.0010"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":22,"model":"SAGN+MCR","metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8441 ± 0.0005","Validation Accuracy":"0.9325 ± 0.0004"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/improving-the-training-of-graph-neural","paper_url":"https://arxiv.org/abs/2112.04319v2","paper_title":"SCR: Training Graph Neural Networks with Consistency Regularization","code":"https://github.com/THUDM/SCR","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":23,"model":"SAGN+SLE","metrics":{"Ext. data":"No","Number of params":"2179678","Test Accuracy":"0.8428 ± 0.0014","Validation Accuracy":"0.9287 ± 0.0003"},"uses_additional_data":false,"paper_date":"2021-04-19","paper":"/paper/scalable-and-adaptive-graph-neural-networks","paper_url":"https://arxiv.org/abs/2104.09376v3","paper_title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","code":"https://github.com/skepsun/SAGN_with_SLE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"MLP + C&S","metrics":{"Ext. data":"No","Number of params":"96247","Test Accuracy":"0.8418 ± 0.0007","Validation Accuracy":"0.9147 ± 0.0009"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":25,"model":"GIANT-XRT+GraphSAINT(use raw text)","metrics":{"Ext. data":"Yes","Number of params":"417583","Test Accuracy":"0.8415 ± 0.0022","Validation Accuracy":"0.9318 ± 0.0004"},"uses_additional_data":false,"paper_date":"2021-10-29","paper":"/paper/node-feature-extraction-by-self-supervised-1","paper_url":"https://arxiv.org/abs/2111.00064v3","paper_title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","code":"https://github.com/amzn/pecos","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":14,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":26,"model":"GraphSAGE","metrics":{"Ext. data":"No","Number of params":"433047","Test Accuracy":"0.8389 ± 0.0036","Validation Accuracy":"0.9242 ± 0.0029"},"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":27,"model":"Polynormer","metrics":{"Ext. data":"No","Number of params":"2383654","Test Accuracy":"0.8382 ± 0.0011","Validation Accuracy":"0.9239 ± 0.0005"},"uses_additional_data":false,"paper_date":"2024-03-02","paper":"/paper/polynormer-polynomial-expressive-graph","paper_url":"https://arxiv.org/abs/2403.01232v3","paper_title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","code":"https://github.com/cornell-zhang/Polynormer/tree/master/large_graph_exp","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"GAMLP","metrics":{"Ext. data":"No","Number of params":"3335831","Test Accuracy":"0.8354 ± 0.0009","Validation Accuracy":"0.9312 ± 0.0003"},"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":29,"model":"AGDN","metrics":{"Ext. data":"No","Number of params":"1544047","Test Accuracy":"0.8334 ± 0.0027","Validation Accuracy":"0.9229 ± 0.0010"},"uses_additional_data":false,"paper_date":"2020-12-30","paper":"/paper/adaptive-graph-diffusion-networks-with-hop","paper_url":"https://arxiv.org/abs/2012.15024v2","paper_title":"Adaptive Graph Diffusion Networks","code":"https://github.com/skepsun/SAGN_with_SLE","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"RevGNN-112","metrics":{"Ext. data":"No","Number of params":"2945007","Test Accuracy":"0.8307 ± 0.0030","Validation Accuracy":"0.9290 ± 0.0007"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/training-graph-neural-networks-with-1000","paper_url":"https://arxiv.org/abs/2106.07476v3","paper_title":"Training Graph Neural Networks with 1000 Layers","code":"https://github.com/lightaime/deep_gcns_torch/tree/master/examples/ogb_eff/ogbn_arxiv_dgl","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"Linear + C&S","metrics":{"Ext. data":"No","Number of params":"10763","Test Accuracy":"0.8301 ± 0.0001","Validation Accuracy":"0.9134 ± 0.0001"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":32,"model":"UniMP","metrics":{"Ext. data":"No","Number of params":"1475605","Test Accuracy":"0.8256 ± 0.0031","Validation Accuracy":"0.9308 ± 0.0017"},"uses_additional_data":false,"paper_date":"2020-09-08","paper":"/paper/masked-label-prediction-unified-massage","paper_url":"https://arxiv.org/abs/2009.03509v5","paper_title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","code":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/unimp","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"Plain Linear + C&S","metrics":{"Ext. data":"No","Number of params":"4747","Test Accuracy":"0.8254 ± 0.0003","Validation Accuracy":"0.9103 ± 0.0001"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":34,"model":"GCN","metrics":{"Ext. data":"No","Number of params":"233047","Test Accuracy":"0.8233 ± 0.0019","Validation Accuracy":"0.9224 ± 0.0036"},"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":35,"model":"DeeperGCN+FLAG","metrics":{"Ext. data":"No","Number of params":"253743","Test Accuracy":"0.8193 ± 0.0031","Validation Accuracy":"0.9221 ± 0.0037"},"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":36,"model":"GAT+FLAG","metrics":{"Ext. data":"No","Number of params":"751574","Test Accuracy":"0.8176 ± 0.0045","Validation Accuracy":"0.9251 ± 0.0006"},"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":37,"model":"GraphSAGE + C&S + node2vec","metrics":{"Ext. data":"No","Number of params":"103983","Test Accuracy":"0.8154 ± 0.0050","Validation Accuracy":"0.9238 ± 0.0006"},"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":38,"model":"SAGN","metrics":{"Ext. data":"No","Number of params":"2233391","Test Accuracy":"0.8120 ± 0.0007","Validation Accuracy":"0.9309 ± 0.0004"},"uses_additional_data":false,"paper_date":"2021-04-19","paper":"/paper/scalable-and-adaptive-graph-neural-networks","paper_url":"https://arxiv.org/abs/2104.09376v3","paper_title":"Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training","code":"https://github.com/skepsun/SAGN_with_SLE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"PCAPass + XGBoost","metrics":{"Ext. data":"No","Number of params":"0","Test Accuracy":"0.8115 ± 0.0002","Validation Accuracy":"0.9200 ± 0.0005"},"uses_additional_data":false,"paper_date":"2022-02-01","paper":"/paper/dimensionality-reduction-meets-message","paper_url":"https://arxiv.org/abs/2202.00408v2","paper_title":"Dimensionality Reduction Meets Message Passing for Graph Node Embeddings","code":"https://github.com/ksadowski13/PCAPass","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"DeeperGCN","metrics":{"Ext. data":"No","Number of params":"253743","Test Accuracy":"0.8098 ± 0.0020","Validation Accuracy":"0.9238 ± 0.0009"},"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":41,"model":"E2EG (use raw text)","metrics":{"Ext. data":"Yes","Number of params":"66793520","Test Accuracy":"0.8098 ± 0.0040","Validation Accuracy":"0.9234 ± 0.0009"},"uses_additional_data":false,"paper_date":"2022-08-09","paper":"/paper/e2eg-end-to-end-node-classification-using","paper_url":"https://arxiv.org/abs/2208.04609v2","paper_title":"E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes","code":"https://github.com/tuanh23/e2eg","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"GAT w/NS + C&S","metrics":{"Ext. data":"No","Number of params":"753622","Test Accuracy":"0.8092 ± 0.0037","Validation Accuracy":"0.9263 ± 0.0008"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":43,"model":"SIGN","metrics":{"Ext. data":"No","Number of params":"3483703","Test Accuracy":"0.8052 ± 0.0016","Validation Accuracy":"0.9299 ± 0.0004"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/sign-scalable-inception-graph-neural-networks","paper_url":"https://arxiv.org/abs/2004.11198v3","paper_title":"SIGN: Scalable Inception Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/sign","n_code_links":5,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"GIANT-XRT+MLP (use raw text)","metrics":{"Ext. data":"Yes","Number of params":"275759","Test Accuracy":"0.8049 ± 0.0028","Validation Accuracy":"0.9210 ± 0.0009"},"uses_additional_data":false,"paper_date":"2021-10-29","paper":"/paper/node-feature-extraction-by-self-supervised-1","paper_url":"https://arxiv.org/abs/2111.00064v3","paper_title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","code":"https://github.com/amzn/pecos","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":14,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"GraphSAGE w/NS + C&S","metrics":{"Ext. data":"No","Number of params":"207919","Test Accuracy":"0.8041 ± 0.0022","Validation Accuracy":"0.9238 ± 0.0007"},"uses_additional_data":false,"paper_date":"2020-10-27","paper":"/paper/combining-label-propagation-and-simple-models-1","paper_url":"https://arxiv.org/abs/2010.13993v2","paper_title":"Combining Label Propagation and Simple Models Out-performs Graph Neural Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/correct_and_smooth","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":46,"model":"GraphSAINT-inductive","metrics":{"Ext. data":"No","Number of params":"331661","Test Accuracy":"0.8027 ± 0.0026","Validation Accuracy":"Please tell us"},"uses_additional_data":false,"paper_date":"2019-07-10","paper":"/paper/graphsaint-graph-sampling-based-inductive","paper_url":"https://arxiv.org/abs/1907.04931v4","paper_title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/graphsaint","n_code_links":8,"syntology":null},{"rank_in_archive_order":47,"model":"ClusterGCN+residual+3 layers","metrics":{"Ext. data":"No","Number of params":"456034","Test Accuracy":"0.7971 ± 0.0042","Validation Accuracy":"0.9188 ± 0.0008"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/cluster-gcn-an-efficient-algorithm-for","paper_url":"https://arxiv.org/abs/1905.07953v2","paper_title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","code":"https://github.com/google-research/google-research","n_code_links":6,"syntology":null},{"rank_in_archive_order":48,"model":"GAT with NeighborSampling","metrics":{"Ext. data":"No","Number of params":"751574","Test Accuracy":"0.7945 ± 0.0059","Validation Accuracy":"Please tell us"},"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":49,"model":"GraphSAGE+FLAG","metrics":{"Ext. data":"No","Number of params":"206895","Test Accuracy":"0.7936 ± 0.0057","Validation Accuracy":"0.9205 ± 0.0007"},"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":50,"model":"Cluster-GAT","metrics":{"Ext. data":"No","Number of params":"1540848","Test Accuracy":"0.7923 ± 0.0078","Validation Accuracy":"0.8985 ± 0.0022"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/cluster-gcn-an-efficient-algorithm-for","paper_url":"https://arxiv.org/abs/1905.07953v2","paper_title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","code":"https://github.com/google-research/google-research","n_code_links":6,"syntology":null},{"rank_in_archive_order":51,"model":"GraphSAINT (SAGE aggr)","metrics":{"Ext. data":"No","Number of params":"206895","Test Accuracy":"0.7908 ± 0.0024","Validation Accuracy":"0.9162 ± 0.0008"},"uses_additional_data":false,"paper_date":"2019-07-10","paper":"/paper/graphsaint-graph-sampling-based-inductive","paper_url":"https://arxiv.org/abs/1907.04931v4","paper_title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/graphsaint","n_code_links":8,"syntology":null},{"rank_in_archive_order":52,"model":"ClusterGCN (SAGE aggr)","metrics":{"Ext. data":"No","Number of params":"206895","Test Accuracy":"0.7897 ± 0.0033","Validation Accuracy":"0.9212 ± 0.0009"},"uses_additional_data":false,"paper_date":"2019-05-20","paper":"/paper/cluster-gcn-an-efficient-algorithm-for","paper_url":"https://arxiv.org/abs/1905.07953v2","paper_title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","code":"https://github.com/google-research/google-research","n_code_links":6,"syntology":null},{"rank_in_archive_order":53,"model":"NeighborSampling (SAGE aggr)","metrics":{"Ext. data":"No","Number of params":"206895","Test Accuracy":"0.7870 ± 0.0036","Validation Accuracy":"0.9170 ± 0.0009"},"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":54,"model":"Full-batch GraphSAGE","metrics":{"Ext. data":"No","Number of params":"206895","Test Accuracy":"0.7850 ± 0.0014","Validation Accuracy":"0.9224 ± 0.0007"},"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":55,"model":"GraphSAGE","metrics":{"Ext. data":"No","Number of params":"Please tell us","Test Accuracy":"0.7829 ± 0.0016","Validation Accuracy":"Please tell us"},"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":56,"model":"TCNN","metrics":{"Ext. data":"No","Number of params":"22624","Test Accuracy":"0.7606 ± 0.0037","Validation Accuracy":"0.8991 ± 0.0011"},"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":57,"model":"Full-batch GCN","metrics":{"Ext. data":"No","Number of params":"103727","Test Accuracy":"0.7564 ± 0.0021","Validation Accuracy":"0.9200 ± 0.0003"},"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":58,"model":"Label Propagation","metrics":{"Ext. data":"No","Number of params":"0","Test Accuracy":"0.7434 ± 0.0000","Validation Accuracy":"0.9091 ± 0.0000"},"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":59,"model":"GraphZoom (Node2vec)","metrics":{"Ext. data":"No","Number of params":"120251183","Test Accuracy":"0.7406 ± 0.0026","Validation Accuracy":"0.9066 ± 0.0011"},"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":60,"model":"Node2vec","metrics":{"Ext. data":"No","Number of params":"313612207","Test Accuracy":"0.7249 ± 0.0010","Validation Accuracy":"0.9032 ± 0.0006"},"uses_additional_data":false,"paper_date":"2016-07-03","paper":"/paper/node2vec-scalable-feature-learning-for","paper_url":"http://arxiv.org/abs/1607.00653v1","paper_title":"node2vec: Scalable Feature Learning for Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/node2vec","n_code_links":20,"syntology":{"n_ran":8,"n_unverified":17,"n_samples":25,"n_pointer_only_licence":3}},{"rank_in_archive_order":61,"model":"GLNN","metrics":{"Test Accuracy":"0.6886 ± 0.0046"},"uses_additional_data":false,"paper_date":"2021-10-17","paper":"/paper/graph-less-neural-networks-teaching-old-mlps-1","paper_url":"https://arxiv.org/abs/2110.08727v2","paper_title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","code":"https://github.com/snap-research/graphless-neural-networks","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":62,"model":"CoLinkDistMLP","metrics":{"Ext. data":"No","Number of params":"115806","Test Accuracy":"0.6259 ± 0.0010","Validation Accuracy":"0.7721 ± 0.0015"},"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":63,"model":"MLP+FLAG","metrics":{"Ext. data":"No","Number of params":"103727","Test Accuracy":"0.6241 ± 0.0016","Validation Accuracy":"0.7688 ± 0.0014"},"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":64,"model":"MLP","metrics":{"Ext. data":"No","Number of params":"103727","Test Accuracy":"0.6106 ± 0.0008","Validation Accuracy":"0.7554 ± 0.0014"},"uses_additional_data":false,"paper_date":"2020-05-02","paper":"/paper/open-graph-benchmark-datasets-for-machine","paper_url":"https://arxiv.org/abs/2005.00687v7","paper_title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","code":"https://github.com/snap-stanford/ogb","n_code_links":21,"syntology":{"n_ran":2,"n_unverified":15,"n_samples":17,"n_pointer_only_licence":15}}],"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":47,"rows_with_any_sample_ran":44,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":132,"n_unverified":195,"n_samples":327,"n_pointer_only_licence":101,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":191,"n_unverified":333,"n_samples":524,"n_pointer_only_licence":135,"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"}}}