{"url":"/sota/link-property-prediction-on-ogbl-wikikg2","task":{"name":"Link Property Prediction","url":"/task/link-property-prediction","note":null},"dataset":{"name":"ogbl-wikikg2","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 MRR","Ext. data","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":{"Test MRR":"higher","Ext. data":null,"Validation MRR":"higher","Number of params":"lower"}},"counts":{"rows":30,"rows_with_code":18,"rows_with_paper_page":23,"rows_dated":23,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"RelEns","metrics":{"Ext. data":"No","Number of params":"2176767622","Test MRR":"0.7392 ± 0.0011","Validation MRR":"0.7509 ± 0.0009"},"uses_additional_data":false,"paper_date":"2023-10-13","paper":"/paper/relation-aware-ensemble-learning-for","paper_url":"https://arxiv.org/abs/2310.08917v1","paper_title":"Relation-aware Ensemble Learning for Knowledge Graph Embedding","code":"https://github.com/lars-research/relens","n_code_links":2,"syntology":null},{"rank_in_archive_order":2,"model":"AutoWeird","metrics":{"Ext. data":"No","Number of params":"19215402","Test MRR":"0.7353 ± 0.0006","Validation MRR":"0.7362 ± 0.0006"},"uses_additional_data":false,"paper_date":"2022-07-24","paper":"/paper/autoweird-weird-translational-scoring","paper_url":"https://arxiv.org/abs/2207.11673v1","paper_title":"AutoWeird: Weird Translational Scoring Function Identified by Random Search","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"StarGraph + TripleRE + Text","metrics":{"Ext. data":"Yes","Number of params":"1927395330","Test MRR":"0.7305 ± 0.0010","Validation MRR":"0.7442 ± 0.0006"},"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":"InterHT+","metrics":{"Ext. data":"No","Number of params":"156332770","Test MRR":"0.7293 ± 0.0018","Validation MRR":"0.7391 ± 0.0023"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/interht-knowledge-graph-embeddings-by","paper_url":"https://arxiv.org/abs/2202.04897v2","paper_title":"InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"InterHT+ (256dim)","metrics":{"Ext. data":"No","Number of params":"148000738","Test MRR":"0.7257 ± 0.0018","Validation MRR":"0.7370 ± 0.0022"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/interht-knowledge-graph-embeddings-by","paper_url":"https://arxiv.org/abs/2202.04897v2","paper_title":"InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"StarGraph + TripleRE","metrics":{"Ext. data":"No","Number of params":"86762146","Test MRR":"0.7201 ± 0.0011","Validation MRR":"0.7288 ± 0.0008"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/stargraph-a-coarse-to-fine-representation","paper_url":"https://arxiv.org/abs/2205.14209v2","paper_title":"StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph","code":"https://github.com/hzli-ucas/stargraph","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":7,"model":"CompoundE3D","metrics":{"Ext. data":"No","Number of params":"750662700","Test MRR":"0.7006 ± 0.0011","Validation MRR":"0.7175 ± 0.0015"},"uses_additional_data":false,"paper_date":"2023-04-01","paper":"/paper/knowledge-graph-embedding-with-3d-compound","paper_url":"https://arxiv.org/abs/2304.00378v1","paper_title":"Knowledge Graph Embedding with 3D Compound Geometric Transformations","code":"https://github.com/hughxiouge/CompoundE3D","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"TranS","metrics":{"Ext. data":"No","Number of params":"19215402","Test MRR":"0.6882 ± 0.0019","Validation MRR":"0.6988 ± 0.0006"},"uses_additional_data":false,"paper_date":"2022-04-18","paper":"/paper/trans-transition-based-knowledge-graph","paper_url":"https://arxiv.org/abs/2204.08401v2","paper_title":"TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"InterHT","metrics":{"Ext. data":"No","Number of params":"19215402","Test MRR":"0.6779 ± 0.0018","Validation MRR":"0.6893 ± 0.0015"},"uses_additional_data":false,"paper_date":"2022-02-10","paper":"/paper/interht-knowledge-graph-embeddings-by","paper_url":"https://arxiv.org/abs/2202.04897v2","paper_title":"InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"A*Net","metrics":{"Ext. data":"No","Number of params":"6831201","Test MRR":"0.6711 ± 0.0045","Validation MRR":"0.6796 ± 0.0070"},"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":"A*Net","metrics":{"Ext. data":"No","Number of params":"6831201","Test MRR":"0.6711 ± 0.0045","Validation MRR":"0.6796 ± 0.0070"},"uses_additional_data":false,"paper_date":"2022-06-07","paper":"/paper/a-net-a-scalable-path-based-reasoning-1","paper_url":"https://arxiv.org/abs/2206.04798v5","paper_title":"A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs","code":"https://github.com/deepgraphlearning/astarnet","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"TripleRE + NodePiece","metrics":{"Ext. data":"No","Number of params":"7289002","Test MRR":"0.6582 ± 0.0020","Validation MRR":"0.6616 ± 0.0018"},"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":"ComplEx-N3-RP (100dim)","metrics":{"Number of params":"500334800","Test MRR":"0.6481","Validation MRR":"0.6701"},"uses_additional_data":false,"paper_date":"2021-10-06","paper":"/paper/relation-prediction-as-an-auxiliary-training","paper_url":"https://arxiv.org/abs/2110.02834v1","paper_title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","code":"https://github.com/facebookresearch/ssl-relation-prediction","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"ComplEx-RP (50dim)","metrics":{"Ext. data":"No","Number of params":"250167400","Test MRR":"0.6392 ± 0.0045","Validation MRR":"0.6561 ± 0.0070"},"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":"ComplEx-N3-RP (50dim)","metrics":{"Number of params":"250167400","Test MRR":"0.6364","Validation MRR":"0.6594"},"uses_additional_data":false,"paper_date":"2021-10-06","paper":"/paper/relation-prediction-as-an-auxiliary-training","paper_url":"https://arxiv.org/abs/2110.02834v1","paper_title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","code":"https://github.com/facebookresearch/ssl-relation-prediction","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"TransERR","metrics":{"Ext. data":"No","Number of params":"500441802","Test MRR":"0.6359 ± 0.0020","Validation MRR":"0.6518 ± 0.0012"},"uses_additional_data":false,"paper_date":"2023-06-26","paper":"/paper/transerr-translation-based-knowledge-graph","paper_url":"https://arxiv.org/abs/2306.14580v2","paper_title":"TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation","code":"https://github.com/dellixx/transerr","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"tripleRE","metrics":{"Ext. data":"No","Number of params":"500763337","Test MRR":"0.5794 ± 0.0020","Validation MRR":"0.6045 ± 0.0024"},"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":"NodePiece + AutoSF","metrics":{"Ext. data":"No","Number of params":"6860602","Test MRR":"0.5703 ± 0.0035","Validation MRR":"0.5806 ± 0.0047"},"uses_additional_data":false,"paper_date":"2021-06-23","paper":"/paper/nodepiece-compositional-and-parameter","paper_url":"https://arxiv.org/abs/2106.12144v2","paper_title":"NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs","code":"https://github.com/migalkin/NodePiece","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"Rot-Pro","metrics":{"Ext. data":"No","Number of params":"1000669602","Test MRR":"0.5602 ± 0.0016","Validation MRR":"0.5740 ± 0.0008"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/rot-pro-modeling-transitivity-by-projection","paper_url":"https://arxiv.org/abs/2110.14450v1","paper_title":"Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding","code":"https://github.com/tewiSong/Rot-Pro","n_code_links":2,"syntology":null},{"rank_in_archive_order":20,"model":"AutoSF","metrics":{"Ext. data":"No","Number of params":"500227800","Test MRR":"0.5458 ± 0.0052","Validation MRR":"0.5510 ± 0.0063"},"uses_additional_data":false,"paper_date":"2019-04-26","paper":"/paper/autokge-searching-scoring-functions-for","paper_url":"https://arxiv.org/abs/1904.11682v3","paper_title":"AutoSF: Searching Scoring Functions for Knowledge Graph Embedding","code":"https://github.com/AutoML-4Paradigm/ERAS","n_code_links":3,"syntology":null},{"rank_in_archive_order":21,"model":"PairRE (200dim)","metrics":{"Ext. data":"No","Number of params":"500334800","Test MRR":"0.5208 ± 0.0027","Validation MRR":"0.5423 ± 0.0020"},"uses_additional_data":false,"paper_date":"2020-11-07","paper":"/paper/pairre-knowledge-graph-embeddings-via-paired","paper_url":"https://arxiv.org/abs/2011.03798v3","paper_title":"PairRE: Knowledge Graph Embeddings via Paired Relation Vectors","code":"https://github.com/ant-research/KnowledgeGraphEmbeddingsViaPairedRelationVectors_PairRE","n_code_links":2,"syntology":null},{"rank_in_archive_order":22,"model":"RotatE (250dim)","metrics":{"Ext. data":"No","Number of params":"1250435750","Test MRR":"0.4332 ± 0.0025","Validation MRR":"0.4353 ± 0.0028"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/rotate-knowledge-graph-embedding-by","paper_url":"http://arxiv.org/abs/1902.10197v1","paper_title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/rotate.py","n_code_links":10,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"RotPro","metrics":{"Ext. data":"No","Number of params":"1000669602","Test MRR":"0.4277 ± 0.0008","Validation MRR":"0.4174 ± 0.0058"},"uses_additional_data":false,"paper_date":"2021-10-27","paper":"/paper/rot-pro-modeling-transitivity-by-projection","paper_url":"https://arxiv.org/abs/2110.14450v1","paper_title":"Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding","code":"https://github.com/tewiSong/Rot-Pro","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"TransE (500dim)","metrics":{"Ext. data":"No","Number of params":"1250569500","Test MRR":"0.4256 ± 0.0030","Validation MRR":"0.4272 ± 0.0030"},"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":25,"model":"ComplEx (250dim)","metrics":{"Ext. data":"No","Number of params":"1250569500","Test MRR":"0.4027 ± 0.0027","Validation MRR":"0.3759 ± 0.0016"},"uses_additional_data":false,"paper_date":"2016-06-20","paper":"/paper/complex-embeddings-for-simple-link-prediction","paper_url":"http://arxiv.org/abs/1606.06357v1","paper_title":"Complex Embeddings for Simple Link Prediction","code":"https://github.com/pyg-team/pytorch_geometric/blob/2947af7733d87315a9218a0bfabbfda10b595f0e/torch_geometric/nn/kge/complex.py","n_code_links":9,"syntology":null},{"rank_in_archive_order":26,"model":"ComplEx (50dim)","metrics":{"Ext. data":"No","Number of params":"250113900","Test MRR":"0.3804 ± 0.0022","Validation MRR":"0.3534 ± 0.0052"},"uses_additional_data":false,"paper_date":"2016-06-20","paper":"/paper/complex-embeddings-for-simple-link-prediction","paper_url":"http://arxiv.org/abs/1606.06357v1","paper_title":"Complex Embeddings for Simple Link Prediction","code":"https://github.com/pyg-team/pytorch_geometric/blob/2947af7733d87315a9218a0bfabbfda10b595f0e/torch_geometric/nn/kge/complex.py","n_code_links":9,"syntology":null},{"rank_in_archive_order":27,"model":"DistMult (500dim)","metrics":{"Ext. data":"No","Number of params":"1250569500","Test MRR":"0.3729 ± 0.0045","Validation MRR":"0.3506 ± 0.0042"},"uses_additional_data":false,"paper_date":"2014-12-20","paper":"/paper/embedding-entities-and-relations-for-learning","paper_url":"http://arxiv.org/abs/1412.6575v4","paper_title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/distmult.py","n_code_links":10,"syntology":null},{"rank_in_archive_order":28,"model":"DistMult (100dim)","metrics":{"Ext. data":"No","Number of params":"250113900","Test MRR":"0.3447 ± 0.0082","Validation MRR":"0.3150 ± 0.0088"},"uses_additional_data":false,"paper_date":"2014-12-20","paper":"/paper/embedding-entities-and-relations-for-learning","paper_url":"http://arxiv.org/abs/1412.6575v4","paper_title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/distmult.py","n_code_links":10,"syntology":null},{"rank_in_archive_order":29,"model":"TransE (100dim)","metrics":{"Ext. data":"No","Number of params":"250113900","Test MRR":"0.2622 ± 0.0045","Validation MRR":"0.2465 ± 0.0020"},"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":30,"model":"RotatE (50dim)","metrics":{"Ext. data":"No","Number of params":"250087150","Test MRR":"0.2530 ± 0.0034","Validation MRR":"0.2250 ± 0.0035"},"uses_additional_data":false,"paper_date":"2019-02-26","paper":"/paper/rotate-knowledge-graph-embedding-by","paper_url":"http://arxiv.org/abs/1902.10197v1","paper_title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/rotate.py","n_code_links":10,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}}],"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":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":15,"n_unverified":10,"n_samples":25,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":10,"n_samples":30,"n_pointer_only_licence":6,"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"}}}