{"url":"/sota/link-property-prediction-on-ogbl-collab","task":{"name":"Link Property Prediction","url":"/task/link-property-prediction","note":null},"dataset":{"name":"ogbl-collab","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 Hits@50","Ext. data","Validation Hits@50","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 Hits@50":null,"Ext. data":null,"Validation Hits@50":null,"Number of params":"lower"}},"counts":{"rows":34,"rows_with_code":22,"rows_with_paper_page":26,"rows_dated":26,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"E2N","metrics":{"Ext. data":"No","Number of params":"526851","Test Hits@50":"0.9515 ± 0.1410","Validation Hits@50":"0.9546 ± 0.1270"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/edge2node-reducing-edge-prediction-to-node","paper_url":"https://arxiv.org/abs/2311.02921v3","paper_title":"Edge2Node: Reducing Edge Prediction to Node Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"HyperFusion","metrics":{"Ext. data":"No","Number of params":"1064446212","Test Hits@50":"0.7129 ± 0.0018","Validation Hits@50":"0.7385 ± 0.0099"},"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":"GIDN@YITU","metrics":{"Ext. data":"No","Number of params":"60449025","Test Hits@50":"0.7096 ± 0.0055","Validation Hits@50":"0.9620 ± 0.0040"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/gidn-a-lightweight-graph-inception-diffusion","paper_url":"https://arxiv.org/abs/2210.01301v3","paper_title":"GIDN: A Lightweight Graph Inception Diffusion Network for High-efficient Link Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"PLNLP + SIGN","metrics":{"Ext. data":"No","Number of params":"34980864","Test Hits@50":"0.7087 ± 0.0033","Validation Hits@50":"1.0000 ± 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":5,"model":"PLNLP (random walk aug.)","metrics":{"Ext. data":"No","Number of params":"34980864","Test Hits@50":"0.7059 ± 0.0029","Validation Hits@50":"1.0000 ± 0.0000"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/pairwise-learning-for-neural-link-prediction","paper_url":"https://arxiv.org/abs/2112.02936v6","paper_title":"Pairwise Learning for Neural Link Prediction","code":"https://github.com/zhitao-wang/PLNLP","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":6,"model":"HOP-REC","metrics":{"Ext. data":"No","Number of params":"30191104","Test Hits@50":"0.7012 ± 0.0016","Validation Hits@50":"1.0000 ± 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":7,"model":"PLNLP+ LRGA","metrics":{"Ext. data":"No","Number of params":"35200656","Test Hits@50":"0.6909 ± 0.0055","Validation Hits@50":"1.0000 ± 0.0000"},"uses_additional_data":false,"paper_date":"2020-06-14","paper":"/paper/from-graph-low-rank-global-attention-to-2-fwl","paper_url":"https://arxiv.org/abs/2006.07846v2","paper_title":"Global Attention Improves Graph Networks Generalization","code":"https://github.com/omri1348/LRGA","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":8,"model":"PLNLP (val as input)","metrics":{"Ext. data":"No","Number of params":"35112192","Test Hits@50":"0.6872 ± 0.0052","Validation Hits@50":"1.0000 ± 0.0000"},"uses_additional_data":false,"paper_date":"2021-12-06","paper":"/paper/pairwise-learning-for-neural-link-prediction","paper_url":"https://arxiv.org/abs/2112.02936v6","paper_title":"Pairwise Learning for Neural Link Prediction","code":"https://github.com/zhitao-wang/PLNLP","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":9,"model":"Refined-GAE","metrics":{"Ext. data":"No","Number of params":"126669825","Test Hits@50":"0.6816 ± 0.0041","Validation Hits@50":"1.0000 ± 0.0000"},"uses_additional_data":false,"paper_date":"2024-11-06","paper":"/paper/reconsidering-the-performance-of-gae-in-link","paper_url":"https://arxiv.org/abs/2411.03845v1","paper_title":"Reconsidering the Performance of GAE in Link Prediction","code":"https://github.com/GraphPKU/Refined-GAE","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"TopoLink","metrics":{"Ext. data":"No","Number of params":"483363845","Test Hits@50":"0.6792 ± 0.0074","Validation Hits@50":"0.6771 ± 0.0083"},"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":11,"model":"S3GRL (PoS Plus)","metrics":{"Ext. data":"No","Number of params":"5913025","Test Hits@50":"0.6683 ± 0.0030","Validation Hits@50":"0.9861 ± 0.0006"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/simplifying-subgraph-representation-learning","paper_url":"https://arxiv.org/abs/2301.12562v4","paper_title":"Simplifying Subgraph Representation Learning for Scalable Link Prediction","code":"https://github.com/venomouscyanide/s3grl","n_code_links":3,"syntology":null},{"rank_in_archive_order":12,"model":"ELPH","metrics":{"Ext. data":"No","Number of params":"3284065","Test Hits@50":"0.6636 ± 0.5876","Validation Hits@50":"0.6631 ± 0.0021"},"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":"BUDDY","metrics":{"Ext. data":"No","Number of params":"1184867","Test Hits@50":"0.6572 ± 0.0053","Validation Hits@50":"0.6621 ± 0.0016"},"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":14,"model":"Adamic Adar+Edge Proposal Set","metrics":{"Ext. data":"No","Number of params":"0","Test Hits@50":"0.6548 ± 0.0000","Validation Hits@50":"0.9735 ± 0.0000"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/edge-proposal-sets-for-link-prediction","paper_url":"https://arxiv.org/abs/2106.15810v1","paper_title":"Edge Proposal Sets for Link Prediction","code":"https://github.com/sangyx/gtrick/tree/main/benchmark/pyg","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"SEAL-nofeat (val as input)","metrics":{"Ext. data":"No","Number of params":"501570","Test Hits@50":"0.6474 ± 0.0043","Validation Hits@50":"0.6495 ± 0.0043"},"uses_additional_data":false,"paper_date":"2020-10-30","paper":"/paper/revisiting-graph-neural-networks-for-link-1","paper_url":"https://arxiv.org/abs/2010.16103v5","paper_title":"Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/seal","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"Adamic Adar","metrics":{"Ext. data":"No","Number of params":"0","Test Hits@50":"0.6417 ± 0.0000","Validation Hits@50":"0.6349 ± 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":17,"model":"Common Neighbor","metrics":{"Ext. data":"No","Number of params":"0","Test Hits@50":"0.6137 ± 0.0000","Validation Hits@50":"0.6036 ± 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":18,"model":"SEAL-nofeat","metrics":{"Ext. data":"No","Number of params":"501570","Test Hits@50":"0.5471 ± 0.0049","Validation Hits@50":"0.6495 ± 0.0043"},"uses_additional_data":false,"paper_date":"2020-10-30","paper":"/paper/revisiting-graph-neural-networks-for-link-1","paper_url":"https://arxiv.org/abs/2010.16103v5","paper_title":"Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/seal","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"GraphSAGE  (val as input)","metrics":{"Ext. data":"No","Number of params":"460289","Test Hits@50":"0.5463 ± 0.0112","Validation Hits@50":"0.5688 ± 0.0077"},"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":20,"model":"NGNN + GraphSAGE","metrics":{"Ext. data":"No","Number of params":"591873","Test Hits@50":"0.5359 ± 0.0056","Validation Hits@50":"0.6281 ± 0.0046"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/network-in-graph-neural-network","paper_url":"https://arxiv.org/abs/2111.11638v1","paper_title":"Network In Graph Neural Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"NGNN + GCN","metrics":{"Ext. data":"No","Number of params":"428033","Test Hits@50":"0.5348 ± 0.0040","Validation Hits@50":"0.6273 ± 0.0040"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/network-in-graph-neural-network","paper_url":"https://arxiv.org/abs/2111.11638v1","paper_title":"Network In Graph Neural Network","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"DeeperGCN","metrics":{"Ext. data":"No","Number of params":"117383","Test Hits@50":"0.5273 ± 0.0047","Validation Hits@50":"0.6187 ± 0.0045"},"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":23,"model":"LRGA + GCN","metrics":{"Ext. data":"No","Number of params":"1069489","Test Hits@50":"0.5221 ± 0.0072","Validation Hits@50":"0.6088 ± 0.0059"},"uses_additional_data":false,"paper_date":"2020-06-14","paper":"/paper/from-graph-low-rank-global-attention-to-2-fwl","paper_url":"https://arxiv.org/abs/2006.07846v2","paper_title":"Global Attention Improves Graph Networks Generalization","code":"https://github.com/omri1348/LRGA","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":24,"model":"Jaccard Index","metrics":{"Ext. data":"No","Number of params":"0","Test Hits@50":"0.5050 ± 0.0000","Validation Hits@50":"0.6098 ± 0.0000"},"uses_additional_data":false,"paper_date":"2025-01-12","paper":"/paper/on-the-effect-of-the-average-clustering","paper_url":"https://arxiv.org/abs/2501.06721v1","paper_title":"On the effect of the average clustering coefficient on topology-based link prediction in featureless graphs","code":"https://github.com/rafiepour/ClusteringEffect","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"DeepWalk","metrics":{"Ext. data":"No","Number of params":"61390187","Test Hits@50":"0.5037 ± 0.0034","Validation Hits@50":"Please tell us"},"uses_additional_data":false,"paper_date":"2014-03-26","paper":"/paper/deepwalk-online-learning-of-social","paper_url":"http://arxiv.org/abs/1403.6652v2","paper_title":"DeepWalk: Online Learning of Social Representations","code":"https://github.com/PaddlePaddle/PaddleRec/tree/master/models/recall/deepwalk","n_code_links":14,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":26,"model":"Node2vec","metrics":{"Ext. data":"No","Number of params":"30322945","Test Hits@50":"0.4888 ± 0.0054","Validation Hits@50":"0.5703 ± 0.0052"},"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":27,"model":"GraphSAGE","metrics":{"Ext. data":"No","Number of params":"460289","Test Hits@50":"0.4810 ± 0.0081","Validation Hits@50":"0.5688 ± 0.0077"},"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":28,"model":"GCN (val as input)","metrics":{"Ext. data":"No","Number of params":"296449","Test Hits@50":"0.4714 ± 0.0145","Validation Hits@50":"0.5263 ± 0.0115"},"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":29,"model":"VQ-GNN (SAGE-Mean)","metrics":{"Test Hits@50":"0.4673 ± 0.0164 ."},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/vq-gnn-a-universal-framework-to-scale-up","paper_url":"https://arxiv.org/abs/2110.14363v1","paper_title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","code":"https://github.com/devnkong/VQ-GNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"GCN","metrics":{"Ext. data":"No","Number of params":"296449","Test Hits@50":"0.4475 ± 0.0107","Validation Hits@50":"0.5263 ± 0.0115"},"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":"VQ-GNN (GCN)","metrics":{"Test Hits@50":"0.4316 ± 0.0134"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/vq-gnn-a-universal-framework-to-scale-up","paper_url":"https://arxiv.org/abs/2110.14363v1","paper_title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","code":"https://github.com/devnkong/VQ-GNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"VQ-GNN (GAT)","metrics":{"Test Hits@50":"0.4102 ± 0.0099"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/vq-gnn-a-universal-framework-to-scale-up","paper_url":"https://arxiv.org/abs/2110.14363v1","paper_title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization","code":"https://github.com/devnkong/VQ-GNN","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"Matrix Factorization","metrics":{"Ext. data":"No","Number of params":"60514049","Test Hits@50":"0.3886 ± 0.0029","Validation Hits@50":"0.4896 ± 0.0029"},"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}},{"rank_in_archive_order":34,"model":"GraphSAGE (val as input)","metrics":{"Number of params":"460289"},"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}}],"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":14,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":64,"n_unverified":58,"n_samples":122,"n_pointer_only_licence":54,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":109,"n_unverified":95,"n_samples":204,"n_pointer_only_licence":94,"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"}}}