{"url":"/sota/link-property-prediction-on-ogbl-citation2","task":{"name":"Link Property Prediction","url":"/task/link-property-prediction","note":null},"dataset":{"name":"ogbl-citation2","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":["Ext. data","Test MRR","Validation MRR","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":{"Ext. data":null,"Test MRR":"higher","Validation MRR":"higher","Number of params":"lower"}},"counts":{"rows":23,"rows_with_code":17,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GraphGPT(d1n30)","metrics":{"Ext. data":"No","Number of params":"133096832","Test MRR":"0.9305 ± 0.0020","Validation MRR":"0.9295 ± 0.0022"},"uses_additional_data":false,"paper_date":"2023-12-31","paper":"/paper/graphgpt-graph-learning-with-generative-pre","paper_url":"https://arxiv.org/abs/2401.00529v1","paper_title":"GraphGPT: Graph Learning with Generative Pre-trained Transformers","code":"https://github.com/alibaba/graph-gpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MPLP","metrics":{"Ext. data":"No","Number of params":"749757283","Test MRR":"0.9072 ± 0.0012","Validation MRR":"0.9074 ± 0.0011"},"uses_additional_data":false,"paper_date":"2023-09-02","paper":"/paper/pure-message-passing-can-estimate-common","paper_url":"https://arxiv.org/abs/2309.00976v4","paper_title":"Pure Message Passing Can Estimate Common Neighbor for Link Prediction","code":"https://github.com/Barcavin/efficient-node-labelling","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":3,"model":"GraphGPT(SMTP)","metrics":{"Ext. data":"No","Number of params":"46784128","Test MRR":"0.9055 ± 0.0016","Validation MRR":"0.9042 ± 0.0014"},"uses_additional_data":false,"paper_date":"2023-12-31","paper":"/paper/graphgpt-graph-learning-with-generative-pre","paper_url":"https://arxiv.org/abs/2401.00529v1","paper_title":"GraphGPT: Graph Learning with Generative Pre-trained Transformers","code":"https://github.com/alibaba/graph-gpt","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CFG","metrics":{"Ext. data":"No","Number of params":"686253","Test MRR":"0.8997 ± 0.0015","Validation MRR":"0.8987 ± 0.0011"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/circle-feature-graphormer-can-circle-features","paper_url":"https://arxiv.org/abs/2309.06574v1","paper_title":"Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?","code":"https://github.com/jingsonglv/CFG","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SIEG","metrics":{"Ext. data":"No","Number of params":"256802","Test MRR":"0.8957 ± 0.0010","Validation MRR":"0.8948 ± 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":6,"model":"GCN + Heuristic Encoding","metrics":{"Ext. data":"No","Number of params":"372674","Test MRR":"0.8891 ± 0.0005","Validation MRR":"0.8892 ± 0.0005"},"uses_additional_data":false,"paper_date":"2024-11-22","paper":"/paper/can-gnns-learn-link-heuristics-a-concise","paper_url":"https://arxiv.org/abs/2411.14711v1","paper_title":"Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods","code":"https://github.com/astroming/GNNHE","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"NGNN + SEAL","metrics":{"Ext. data":"No","Number of params":"1134402","Test MRR":"0.8891 ± 0.0022","Validation MRR":"0.8879 ± 0.0022"},"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":8,"model":"SUREL","metrics":{"Ext. data":"No","Number of params":"79617","Test MRR":"0.8883 ± 0.0018","Validation MRR":"0.8891 ± 0.0021"},"uses_additional_data":false,"paper_date":"2022-02-28","paper":"/paper/algorithm-and-system-co-design-for-efficient","paper_url":"https://arxiv.org/abs/2202.13538v2","paper_title":"Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning","code":"https://github.com/graph-com/surel","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"S3GRL (PoS Plus)","metrics":{"Ext. data":"No","Number of params":"142275001","Test MRR":"0.8814 ± 0.0008","Validation MRR":"0.8809 ± 0.0074"},"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":10,"model":"BUDDY","metrics":{"Ext. data":"No","Number of params":"166531","Test MRR":"0.8796 ± 0.0008","Validation MRR":"0.8793 ± 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":11,"model":"SEAL","metrics":{"Ext. data":"No","Number of params":"260802","Test MRR":"0.8767 ± 0.0032","Validation MRR":"0.8757 ± 0.0031"},"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":12,"model":"AGDN w/GraphSAINT","metrics":{"Ext. data":"No","Number of params":"306716","Test MRR":"0.8549 ± 0.0029","Validation MRR":"0.8556 ± 0.0033"},"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":13,"model":"PLNLP","metrics":{"Ext. data":"No","Number of params":"146514551","Test MRR":"0.8492 ± 0.0029","Validation MRR":"0.8490 ± 0.0031"},"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":14,"model":"Full-batch GCN","metrics":{"Ext. data":"No","Number of params":"296449","Test MRR":"0.8474 ± 0.0021","Validation MRR":"0.8479 ± 0.0023"},"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":15,"model":"HPE - Pre-trained Initialized","metrics":{"Ext. data":"No","Number of params":"749558528","Test MRR":"0.8432 ± 0.0003","Validation MRR":"0.8422 ± 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":16,"model":"Full-batch GraphSAGE","metrics":{"Ext. data":"No","Number of params":"460289","Test MRR":"0.8260 ± 0.0036","Validation MRR":"0.8263 ± 0.0033"},"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":17,"model":"NeighborSampling (SAGE aggr)","metrics":{"Ext. data":"No","Number of params":"460289","Test MRR":"0.8044 ± 0.0010","Validation MRR":"0.8054 ± 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":18,"model":"ClusterGCN (GCN aggr)","metrics":{"Ext. data":"No","Number of params":"296449","Test MRR":"0.8004 ± 0.0025","Validation MRR":"0.7994 ± 0.0025"},"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":19,"model":"GraphSAINT (GCN aggr)","metrics":{"Ext. data":"No","Number of params":"296449","Test MRR":"0.7985 ± 0.0040","Validation MRR":"0.7975 ± 0.0039"},"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":20,"model":"Node2vec","metrics":{"Ext. data":"No","Number of params":"374911105","Test MRR":"0.6141 ± 0.0011","Validation MRR":"0.6124 ± 0.0011"},"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":21,"model":"Adamic Adar","metrics":{"Ext. data":"No","Number of params":"0","Test MRR":"0.5189 ± 0.0000","Validation MRR":"0.5167 ± 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":22,"model":"Matrix Factorization","metrics":{"Ext. data":"No","Number of params":"281113505","Test MRR":"0.5186 ± 0.0443","Validation MRR":"0.5181 ± 0.0436"},"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":23,"model":"Common Neighbor","metrics":{"Ext. data":"No","Number of params":"0","Test MRR":"0.5147 ± 0.0000","Validation MRR":"0.5119 ± 0.0000"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null}],"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":10,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":9,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":70,"n_unverified":62,"n_samples":132,"n_pointer_only_licence":59,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":73,"n_unverified":64,"n_samples":137,"n_pointer_only_licence":64,"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"}}}