{"url":"/sota/node-property-prediction-on-ogbn-mag","task":{"name":"Node Property Prediction","url":"/task/node-property-prediction","note":null},"dataset":{"name":"ogbn-mag","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":39,"rows_with_code":34,"rows_with_paper_page":34,"rows_dated":34,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"LDHGNN","metrics":{"Ext. data":"No","Number of params":"7720368","Test Accuracy":"0.8789 ± 0.0024","Validation Accuracy":"0.8836 ± 0.0028"},"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":"CLGNN","metrics":{"Ext. data":"No","Number of params":"7720368","Test Accuracy":"0.7956 ± 0.0047","Validation Accuracy":"0.8021 ± 0.0020"},"uses_additional_data":false,"paper_date":"2024-02-29","paper":"/paper/loss-aware-curriculum-learning-for","paper_url":"https://arxiv.org/abs/2402.18875v1","paper_title":"Loss-aware Curriculum Learning for Heterogeneous Graph Neural Networks","code":"https://github.com/calderkatyal/CPSC483FinalProject","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"HGAMLP+LP+MS(LINE embs)","metrics":{"Ext. data":"No","Number of params":"8469021","Test Accuracy":"0.5794 ± 0.0018","Validation Accuracy":"0.5997 ± 0.0012"},"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":"LMSPS (w/o embs)","metrics":{"Ext. data":"No","Number of params":"16470044","Test Accuracy":"0.5784 ± 0.0022","Validation Accuracy":"0.5951 ± 0.0007"},"uses_additional_data":false,"paper_date":"2023-07-17","paper":"/paper/long-range-dependency-based-multi-layer","paper_url":"https://arxiv.org/abs/2307.08430v6","paper_title":"Long-range Meta-path Search on Large-scale Heterogeneous Graphs","code":"https://github.com/jhl-hust/lmsps","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":5,"model":"RpHGNN+LP+CR (LINE embs)","metrics":{"Ext. data":"No","Number of params":"7720368","Test Accuracy":"0.5773 ± 0.0012","Validation Accuracy":"0.5973 ± 0.0008"},"uses_additional_data":false,"paper_date":"2023-10-23","paper":"/paper/efficient-heterogeneous-graph-learning-via","paper_url":"https://arxiv.org/abs/2310.14481v2","paper_title":"Efficient Heterogeneous Graph Learning via Random Projection","code":"https://github.com/CrawlScript/RpHGNN","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":6,"model":"LMSPS(w/o ComplEx embs)","metrics":{"Ext. data":"No","Number of params":"16470044","Test Accuracy":"0.5767 ± 0.0015","Validation Accuracy":"0.5902 ± 0.0016"},"uses_additional_data":false,"paper_date":"2023-07-17","paper":"/paper/long-range-dependency-based-multi-layer","paper_url":"https://arxiv.org/abs/2307.08430v6","paper_title":"Long-range Meta-path Search on Large-scale Heterogeneous Graphs","code":"https://github.com/jhl-hust/lmsps","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":7,"model":"PSHGCN (ComplEx embs)","metrics":{"Ext. data":"No","Number of params":"4852434","Test Accuracy":"0.5752 ± 0.0011","Validation Accuracy":"0.5943 ± 0.0015"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/spectral-heterogeneous-graph-convolutions-via","paper_url":"https://arxiv.org/abs/2305.19872v3","paper_title":"Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials","code":"https://github.com/ivam-he/PSHGCN/tree/main/ogbn-mag","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"PSHGCN","metrics":{"Ext. data":"No","Number of params":"4852434","Test Accuracy":"0.5752 ± 0.0011","Validation Accuracy":"0.5943 ± 0.0015"},"uses_additional_data":false,"paper_date":"2023-05-31","paper":"/paper/spectral-heterogeneous-graph-convolutions-via","paper_url":"https://arxiv.org/abs/2305.19872v3","paper_title":"Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials","code":"https://github.com/ivam-he/PSHGCN/tree/main/ogbn-mag","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"LDMLP(w/o ComplEx embs)","metrics":{"Ext. data":"No","Number of params":"13177884","Test Accuracy":"0.5739 ± 0.0012","Validation Accuracy":"0.5888 ± 0.0015"},"uses_additional_data":false,"paper_date":"2023-07-17","paper":"/paper/long-range-dependency-based-multi-layer","paper_url":"https://arxiv.org/abs/2307.08430v6","paper_title":"Long-range Meta-path Search on Large-scale Heterogeneous Graphs","code":"https://github.com/jhl-hust/lmsps","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":10,"model":"SeHGNN (ComplEx embs)","metrics":{"Ext. data":"No","Number of params":"8371231","Test Accuracy":"0.5719 ± 0.0012","Validation Accuracy":"0.5917 ± 0.0009"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/simple-and-efficient-heterogeneous-graph","paper_url":"https://arxiv.org/abs/2207.02547v3","paper_title":"Simple and Efficient Heterogeneous Graph Neural Network","code":"https://github.com/ict-gimlab/sehgnn","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"SeHGNN","metrics":{"Ext. data":"No","Number of params":"8371231","Test Accuracy":"0.5671 ± 0.0014","Validation Accuracy":"0.5870 ± 0.0008"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/simple-and-efficient-heterogeneous-graph","paper_url":"https://arxiv.org/abs/2207.02547v3","paper_title":"Simple and Efficient Heterogeneous Graph Neural Network","code":"https://github.com/ict-gimlab/sehgnn","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"NARS-GAMLP+RLU+SCR","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5631 ± 0.0021","Validation Accuracy":"0.5734 ± 0.0035"},"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":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":13,"model":"NARS-GAMLP+RLU","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5590 ± 0.0027","Validation Accuracy":"0.5702 ± 0.0041"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/graph-attention-multi-layer-perceptron-1","paper_url":"https://arxiv.org/abs/2206.04355v1","paper_title":"Graph Attention Multi-Layer Perceptron","code":"https://github.com/pku-dair/gamlp","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"NARS-GAMLP+RLU","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5590 ± 0.0027","Validation Accuracy":"0.5702 ± 0.0041"},"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":15,"model":"NARS-GAMLP+SCR-m","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5451 ± 0.0019","Validation Accuracy":"0.5590 ± 0.0028"},"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":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"NARS_SAGN+SLE","metrics":{"Ext. data":"No","Number of params":"3846330","Test Accuracy":"0.5440 ± 0.0015","Validation Accuracy":"0.5591 ± 0.0017"},"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":17,"model":"NARS-GAMLP+SCR","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5432 ± 0.0018","Validation Accuracy":"0.5654 ± 0.0021"},"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":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"NARS-GAMLP","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5396 ± 0.0018","Validation Accuracy":"0.5548 ± 0.0008"},"uses_additional_data":false,"paper_date":"2022-06-09","paper":"/paper/graph-attention-multi-layer-perceptron-1","paper_url":"https://arxiv.org/abs/2206.04355v1","paper_title":"Graph Attention Multi-Layer Perceptron","code":"https://github.com/pku-dair/gamlp","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"NARS-GAMLP","metrics":{"Ext. data":"No","Number of params":"6734882","Test Accuracy":"0.5396 ± 0.0018","Validation Accuracy":"0.5548 ± 0.0008"},"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":20,"model":"LEGNN + AS-Train","metrics":{"Ext. data":"No","Number of params":"5147997","Test Accuracy":"0.5378 ± 0.0016","Validation Accuracy":"0.5528 ± 0.0013"},"uses_additional_data":false,"paper_date":"2022-05-31","paper":"/paper/label-enhanced-graph-neural-network-for-semi","paper_url":"https://arxiv.org/abs/2205.15653v2","paper_title":"Label-Enhanced Graph Neural Network for Semi-supervised Node Classification","code":"https://github.com/yule-BUAA/LEGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"LEGNN","metrics":{"Ext. data":"No","Number of params":"5147997","Test Accuracy":"0.5276 ± 0.0014","Validation Accuracy":"0.5443 ± 0.0009"},"uses_additional_data":false,"paper_date":"2022-05-31","paper":"/paper/label-enhanced-graph-neural-network-for-semi","paper_url":"https://arxiv.org/abs/2205.15653v2","paper_title":"Label-Enhanced Graph Neural Network for Semi-supervised Node Classification","code":"https://github.com/yule-BUAA/LEGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"NARS","metrics":{"Ext. data":"No","Number of params":"4130149","Test Accuracy":"0.5240 ± 0.0016","Validation Accuracy":"0.5372 ± 0.0009"},"uses_additional_data":false,"paper_date":"2020-11-19","paper":"/paper/scalable-graph-neural-networks-for-1","paper_url":"https://arxiv.org/abs/2011.09679v1","paper_title":"Scalable Graph Neural Networks for Heterogeneous Graphs","code":"https://github.com/facebookresearch/NARS","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"R-HGNN","metrics":{"Ext. data":"No","Number of params":"5638053","Test Accuracy":"0.5204 ± 0.0026","Validation Accuracy":"0.5361 ± 0.0022"},"uses_additional_data":false,"paper_date":"2021-05-24","paper":"/paper/heterogeneous-graph-representation-learning","paper_url":"https://arxiv.org/abs/2105.11122v2","paper_title":"Heterogeneous Graph Representation Learning with Relation Awareness","code":"https://github.com/yule-BUAA/R-HGNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"R-GSN + metapath2vec","metrics":{"Ext. data":"No","Number of params":"309777252","Test Accuracy":"0.5109 ± 0.0038","Validation Accuracy":"0.5295 ± 0.0042"},"uses_additional_data":false,"paper_date":"2021-05-18","paper":"/paper/residual-network-and-embedding-usage-new","paper_url":"https://arxiv.org/abs/2105.08330v2","paper_title":"Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks","code":"https://github.com/ytchx1999/PyG-OGB-Tricks/tree/main/DGL-ogbn-arxiv","n_code_links":4,"syntology":null},{"rank_in_archive_order":25,"model":"HGConv","metrics":{"Ext. data":"No","Number of params":"2850405","Test Accuracy":"0.5045 ± 0.0017","Validation Accuracy":"0.5300 ± 0.0018"},"uses_additional_data":false,"paper_date":"2020-12-29","paper":"/paper/hybrid-micro-macro-level-convolution-for","paper_url":"https://arxiv.org/abs/2012.14722v1","paper_title":"Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning","code":"https://github.com/yule-BUAA/HGConv","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"R-GSN","metrics":{"Ext. data":"No","Number of params":"154373028","Test Accuracy":"0.5032 ± 0.0037","Validation Accuracy":"0.5182 ± 0.0041"},"uses_additional_data":false,"paper_date":"2017-03-17","paper":"/paper/modeling-relational-data-with-graph","paper_url":"http://arxiv.org/abs/1703.06103v4","paper_title":"Modeling Relational Data with Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/tensorflow/rgcn","n_code_links":27,"syntology":{"n_ran":10,"n_unverified":22,"n_samples":32,"n_pointer_only_licence":15}},{"rank_in_archive_order":27,"model":"HGT (TransE embs)","metrics":{"Ext. data":"No","Number of params":"26877657","Test Accuracy":"0.4982 ± 0.0013","Validation Accuracy":"0.5124 ± 0.0046"},"uses_additional_data":false,"paper_date":"2020-03-03","paper":"/paper/heterogeneous-graph-transformer","paper_url":"https://arxiv.org/abs/2003.01332v1","paper_title":"Heterogeneous Graph Transformer","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hgt","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"GraphSAINT + metapath2vec","metrics":{"Ext. data":"No","Number of params":"309764724","Test Accuracy":"0.4966 ± 0.0022","Validation Accuracy":"0.5066 ± 0.0017"},"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":29,"model":"HGT (LADIES Sample)","metrics":{"Ext. data":"No","Number of params":"21173389","Test Accuracy":"0.4927 ± 0.0061","Validation Accuracy":"0.4989 ± 0.0047"},"uses_additional_data":false,"paper_date":"2020-03-03","paper":"/paper/heterogeneous-graph-transformer","paper_url":"https://arxiv.org/abs/2003.01332v1","paper_title":"Heterogeneous Graph Transformer","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/hgt","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"GraphSAINT (R-GCN aggr)","metrics":{"Ext. data":"No","Number of params":"154366772","Test Accuracy":"0.4751 ± 0.0022","Validation Accuracy":"0.4837 ± 0.0026"},"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":31,"model":"R-GCN+FLAG","metrics":{"Ext. data":"No","Number of params":"154366772","Test Accuracy":"0.4737 ± 0.0048","Validation Accuracy":"0.4835 ± 0.0036"},"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":"NeighborSampling (R-GCN aggr)","metrics":{"Ext. data":"No","Number of params":"154366772","Test Accuracy":"0.4678 ± 0.0067","Validation Accuracy":"0.4761 ± 0.0068"},"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":33,"model":"SIGN","metrics":{"Ext. data":"No","Number of params":"3724645","Test Accuracy":"0.4046 ± 0.0012","Validation Accuracy":"0.4068 ± 0.0010"},"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":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"Full-batch R-GCN","metrics":{"Ext. data":"No","Number of params":"154366772","Test Accuracy":"0.3977 ± 0.0046","Validation Accuracy":"0.4084 ± 0.0041"},"uses_additional_data":false,"paper_date":"2017-03-17","paper":"/paper/modeling-relational-data-with-graph","paper_url":"http://arxiv.org/abs/1703.06103v4","paper_title":"Modeling Relational Data with Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/tensorflow/rgcn","n_code_links":27,"syntology":{"n_ran":10,"n_unverified":22,"n_samples":32,"n_pointer_only_licence":15}},{"rank_in_archive_order":35,"model":"ClusterGCN (R-GCN aggr)","metrics":{"Ext. data":"No","Number of params":"154366772","Test Accuracy":"0.3732 ± 0.0037","Validation Accuracy":"0.3840 ± 0.0031"},"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":36,"model":"MetaPath2vec","metrics":{"Ext. data":"No","Number of params":"94479069","Test Accuracy":"0.3544 ± 0.0036","Validation Accuracy":"0.3506 ± 0.0017"},"uses_additional_data":false,"paper_date":"2017-08-01","paper":"/paper/metapath2vec-scalable-representation-learning","paper_url":"https://dl.acm.org/doi/10.1145/3097983.3098036","paper_title":"metapath2vec: Scalable Representation Learning for Heterogeneous Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/metapath2vec","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"MetaPath2vec","metrics":{"Ext. data":"No","Number of params":"94479069","Test Accuracy":"0.3544 ± 0.0036","Validation Accuracy":"0.3506 ± 0.0017"},"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":38,"model":"CoLinkDistMLP","metrics":{"Ext. data":"No","Number of params":"278202","Test Accuracy":"0.2761 ± 0.0018","Validation Accuracy":"0.2646 ± 0.0013"},"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":39,"model":"MLP","metrics":{"Ext. data":"No","Number of params":"188509","Test Accuracy":"0.2692 ± 0.0026","Validation Accuracy":"0.2626 ± 0.0016"},"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":12,"n_unverified":5,"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 6,885 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":17,"rows_with_any_sample_ran":16,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":10,"samples_over_distinct_papers":{"n_ran":44,"n_unverified":63,"n_samples":107,"n_pointer_only_licence":52,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":65,"n_unverified":100,"n_samples":165,"n_pointer_only_licence":83,"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"}}}