{"url":"/sota/link-prediction-on-yago3-10","task":{"name":"Link Prediction","url":"/task/link-prediction","note":null},"dataset":{"name":"YAGO3-10","url":"/dataset/yago3-10"},"category":"Natural Language Processing","categories":["Graphs","Natural Language Processing"],"category_note":null,"description":"**Link Prediction** is a task in graph and network analysis where the goal is to predict missing or future connections between nodes in a network. Given a partially observed network, the goal of link prediction is to infer which links are most likely to be added or missing based on the observed connections and the structure of the network.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Inductive Representation Learning on Large Graphs](https://arxiv.org/pdf/1706.02216v4.pdf) )</span>","description_from":"task","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":["Hits@1","Hits@3","Hits@10","MRR","MR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Hits@1":null,"Hits@3":null,"Hits@10":null,"MRR":"higher","MR":null}},"counts":{"rows":18,"rows_with_code":16,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MEIM","metrics":{"Hits@1":"0.514","Hits@10":"0.716","Hits@3":"0.625","MRR":"0.585"},"uses_additional_data":false,"paper_date":"2022-09-30","paper":"/paper/meim-multi-partition-embedding-interaction","paper_url":"https://arxiv.org/abs/2209.15597v2","paper_title":"MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction","code":"https://github.com/tranhungnghiep/AnalyzingKGEmbeddings","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":2,"model":"ComplEx-DURA (large model)","metrics":{"Hits@1":"0.511","Hits@10":"0.713","MRR":"0.584"},"uses_additional_data":false,"paper_date":"2020-11-11","paper":"/paper/duality-induced-regularizer-for-tensor","paper_url":"https://arxiv.org/abs/2011.05816v2","paper_title":"Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion","code":"https://github.com/MIRALab-USTC/KGE-HAKE","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"CP-DURA (large model)","metrics":{"Hits@1":"0.506","Hits@10":"0.709","MRR":"0.579"},"uses_additional_data":false,"paper_date":"2020-11-11","paper":"/paper/duality-induced-regularizer-for-tensor","paper_url":"https://arxiv.org/abs/2011.05816v2","paper_title":"Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion","code":"https://github.com/MIRALab-USTC/KGE-HAKE","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"MEI","metrics":{"Hits@1":"0.505","Hits@10":"0.709","Hits@3":"0.622","MR":"756","MRR":"0.578"},"uses_additional_data":false,"paper_date":"2020-06-29","paper":"/paper/multi-partition-embedding-interaction-with","paper_url":"https://arxiv.org/abs/2006.16365v2","paper_title":"Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion","code":"https://github.com/tranhungnghiep/AnalyzeKGE","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"RefE","metrics":{"Hits@1":"0.503","Hits@10":"0.712","Hits@3":"0.621","MRR":"0.577"},"uses_additional_data":false,"paper_date":"2020-05-01","paper":"/paper/low-dimensional-hyperbolic-knowledge-graph-1","paper_url":"https://arxiv.org/abs/2005.00545v1","paper_title":"Low-Dimensional Hyperbolic Knowledge Graph Embeddings","code":"https://github.com/tensorflow/neural-structured-learning/tree/master/research/kg_hyp_emb","n_code_links":3,"syntology":{"n_ran":4,"n_unverified":7,"n_samples":11,"n_pointer_only_licence":8}},{"rank_in_archive_order":6,"model":"BoxE","metrics":{"Hits@1":"0.494","Hits@10":"0.699","MRR":"0.567"},"uses_additional_data":false,"paper_date":"2020-07-13","paper":"/paper/boxe-a-box-embedding-model-for-knowledge-base","paper_url":"https://arxiv.org/abs/2007.06267v2","paper_title":"BoxE: A Box Embedding Model for Knowledge Base Completion","code":"https://github.com/ralphabb/BoxE","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"SAFRAN (white box, rule based)","metrics":{"Hits@1":"0.492","Hits@10":"0.693","MRR":"0.564"},"uses_additional_data":false,"paper_date":"2021-09-16","paper":"/paper/safran-an-interpretable-rule-based-link","paper_url":"https://arxiv.org/abs/2109.08002v1","paper_title":"SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models","code":"https://github.com/OpenBioLink/SAFRAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"NBFNet","metrics":{"Hits@1":"0.480","Hits@10":"0.708","Hits@3":"0.612","MRR":"0.563"},"uses_additional_data":false,"paper_date":"2021-06-13","paper":"/paper/neural-bellman-ford-networks-a-general-graph","paper_url":"https://arxiv.org/abs/2106.06935v4","paper_title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","code":"https://github.com/DeepGraphLearning/NBFNet","n_code_links":3,"syntology":{"n_ran":10,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"A*Net","metrics":{"Hits@1":"0.470","Hits@10":"0.707","Hits@3":"0.611","MRR":"0.556"},"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":10,"model":"DensE","metrics":{"Hits@1":"0.465","Hits@10":"0.678","Hits@3":"0.585","MRR":"0.541"},"uses_additional_data":false,"paper_date":"2020-08-11","paper":"/paper/dense-an-enhanced-non-abelian-group","paper_url":"https://arxiv.org/abs/2008.04548v2","paper_title":"DensE: An Enhanced Non-commutative Representation for Knowledge Graph Embedding with Adaptive Semantic Hierarchy","code":"https://github.com/anonymous-dense-submission/DensE","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"HAKE","metrics":{"Hits@1":"0.462","Hits@10":"0.694","Hits@3":"0.596","MRR":"0.545"},"uses_additional_data":false,"paper_date":"2019-11-21","paper":"/paper/learning-hierarchy-aware-knowledge-graph","paper_url":"https://arxiv.org/abs/1911.09419v3","paper_title":"Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction","code":"https://github.com/MIRALab-USTC/KGE-HAKE","n_code_links":9,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"InteractE","metrics":{"Hits@1":"0.462","Hits@10":"0.687","MRR":"0.541"},"uses_additional_data":false,"paper_date":"2019-11-01","paper":"/paper/interacte-improving-convolution-based","paper_url":"https://arxiv.org/abs/1911.00219v3","paper_title":"InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions","code":"https://github.com/malllabiisc/InteractE","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"Rot-Pro","metrics":{"Hits@1":"0.443","Hits@10":"0.699","Hits@3":"0.596","MRR":"0.542"},"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":14,"model":"DihEdral","metrics":{"Hits@1":"0.381","Hits@10":"0.643","Hits@3":"0.523","MRR":"0.472"},"uses_additional_data":false,"paper_date":"2019-06-03","paper":"/paper/190600687","paper_url":"https://arxiv.org/abs/1906.00687v1","paper_title":"Relation Embedding with Dihedral Group in Knowledge Graph","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"ComplEx-N3 (large model, reciprocal)","metrics":{"Hits@10":"0.71"},"uses_additional_data":false,"paper_date":"2018-06-19","paper":"/paper/canonical-tensor-decomposition-for-knowledge","paper_url":"http://arxiv.org/abs/1806.07297v1","paper_title":"Canonical Tensor Decomposition for Knowledge Base Completion","code":"https://github.com/facebookresearch/kbc","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":16,"model":"ConvE","metrics":{"Hits@10":"0.62","MRR":"0.44"},"uses_additional_data":false,"paper_date":"2017-07-05","paper":"/paper/convolutional-2d-knowledge-graph-embeddings","paper_url":"http://arxiv.org/abs/1707.01476v6","paper_title":"Convolutional 2D Knowledge Graph Embeddings","code":"https://github.com/TimDettmers/ConvE","n_code_links":8,"syntology":null},{"rank_in_archive_order":17,"model":"ComplEx-N3 (reciprocal)","metrics":{"MRR":"0.58"},"uses_additional_data":false,"paper_date":"2018-06-19","paper":"/paper/canonical-tensor-decomposition-for-knowledge","paper_url":"http://arxiv.org/abs/1806.07297v1","paper_title":"Canonical Tensor Decomposition for Knowledge Base Completion","code":"https://github.com/facebookresearch/kbc","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":18,"model":"ComplEx","metrics":{"MRR":"0.551"},"uses_additional_data":false,"paper_date":"2022-07-11","paper":"/paper/start-small-think-big-on-hyperparameter","paper_url":"https://arxiv.org/abs/2207.04979v1","paper_title":"Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings","code":"https://github.com/uma-pi1/dist-kge","n_code_links":2,"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 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":9,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":29,"n_unverified":18,"n_samples":47,"n_pointer_only_licence":20,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":31,"n_unverified":20,"n_samples":51,"n_pointer_only_licence":24,"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"}}}