{"url":"/sota/link-prediction-on-wn18","task":{"name":"Link Prediction","url":"/task/link-prediction","note":null},"dataset":{"name":"WN18","url":"/dataset/wn18"},"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@10","Hits@3","Hits@1","MRR","MR","training time (s)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Hits@10":null,"Hits@3":null,"Hits@1":null,"MRR":"higher","MR":null,"training time (s)":"lower"}},"counts":{"rows":37,"rows_with_code":32,"rows_with_paper_page":37,"rows_dated":37,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Inverse Model","metrics":{"Hits@1":"0.953","Hits@10":"0.964","Hits@3":"0.964","MR":"740","MRR":"0.963"},"uses_additional_data":true,"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":2,"model":"LineaRE","metrics":{"Hits@1":"0.947","Hits@10":"0.961","Hits@3":"0.955","MR":"170","MRR":"0.952"},"uses_additional_data":false,"paper_date":"2020-04-21","paper":"/paper/knowledge-graph-embedding-with-linear","paper_url":"https://arxiv.org/abs/2004.10037v2","paper_title":"LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction","code":"https://github.com/pengyanhui/LineaRE","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"QuatDE","metrics":{"Hits@1":"0.944","Hits@10":"0.961","Hits@3":"0.954","MR":"120","MRR":"0.95"},"uses_additional_data":false,"paper_date":"2021-05-19","paper":"/paper/quatde-dynamic-quaternion-embedding-for","paper_url":"https://arxiv.org/abs/2105.09002v2","paper_title":"QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion","code":"https://github.com/hopkin-ghp/QuatDE","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"AutoKGE","metrics":{"Hits@10":"0.961","MRR":"0.952"},"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":5,"model":"MEI (small)","metrics":{"Hits@1":"0.946","Hits@10":"0.960","Hits@3":"0.953","MRR":"0.951"},"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":6,"model":"ComplEx-N3 (reciprocal)","metrics":{"Hits@10":"0.96"},"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":7,"model":"QuatE","metrics":{"Hits@1":"0.945","Hits@10":"0.959","Hits@3":"0.954","MR":"162","MRR":"0.95"},"uses_additional_data":false,"paper_date":"2019-04-23","paper":"/paper/quaternion-knowledge-graph-embedding","paper_url":"https://arxiv.org/abs/1904.10281v3","paper_title":"Quaternion Knowledge Graph Embeddings","code":"https://github.com/cheungdaven/QuatE","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"DensE","metrics":{"Hits@1":"0.945","Hits@10":"0.959","Hits@3":"0.954","MR":"285","MRR":"0.950"},"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":9,"model":"RotatE","metrics":{"Hits@1":"0.944","Hits@10":"0.959","Hits@3":"0.952","MR":"309","MRR":"0.949"},"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":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"TuckER","metrics":{"Hits@1":"0.949","Hits@10":"0.958","Hits@3":"0.955","MRR":"0.953"},"uses_additional_data":false,"paper_date":"2019-01-28","paper":"/paper/tucker-tensor-factorization-for-knowledge","paper_url":"https://arxiv.org/abs/1901.09590v2","paper_title":"TuckER: Tensor Factorization for Knowledge Graph Completion","code":"https://github.com/Sujit-O/pykg2vec","n_code_links":5,"syntology":null},{"rank_in_archive_order":11,"model":"HypER","metrics":{"Hits@1":"0.947","Hits@10":"0.958","Hits@3":"0.955","MRR":"0.951"},"uses_additional_data":false,"paper_date":"2018-08-21","paper":"/paper/hypernetwork-knowledge-graph-embeddings","paper_url":"https://arxiv.org/abs/1808.07018v5","paper_title":"Hypernetwork Knowledge Graph Embeddings","code":"https://github.com/ibalazevic/HypER","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"ConvR","metrics":{"Hits@1":"0.947","Hits@10":"0.958","Hits@3":"0.955","MRR":"0.951"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/adaptive-convolution-for-multi-relational","paper_url":"https://aclanthology.org/N19-1103","paper_title":"Adaptive Convolution for Multi-Relational Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"MEI-BTD","metrics":{"Hits@1":"0.946","Hits@10":"0.957","Hits@3":"0.952","MRR":"0.950"},"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":14,"model":"pRotatE","metrics":{"Hits@1":"0.942","Hits@10":"0.957","Hits@3":"0.950","MR":"254","MRR":"0.947"},"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":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"OPTransE","metrics":{"Hits@10":"0.957","MR":"199"},"uses_additional_data":false,"paper_date":"2019-09-26","paper":"/paper/representation-learning-with-ordered-relation","paper_url":"https://arxiv.org/abs/1909.11864v1","paper_title":"Representation Learning with Ordered Relation Paths for Knowledge Graph Completion","code":"https://github.com/Peter7Yao/OPTransE","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"Quaternion","metrics":{"Hits@1":"0.931","Hits@10":"0.956","Hits@3":"0.950","MRR":"0.941"},"uses_additional_data":false,"paper_date":"2019-03-27","paper":"/paper/analyzing-knowledge-graph-embedding-methods","paper_url":"https://arxiv.org/abs/1903.11406v4","paper_title":"Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective","code":"https://github.com/tranhungnghiep/AnalyzeKGE","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"ConvE","metrics":{"Hits@1":"0.935","Hits@10":"0.956","Hits@3":"0.946","MR":"374","MRR":"0.943"},"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":18,"model":"MDE","metrics":{"Hits@10":"0.956","MR":"118","MRR":"0.871"},"uses_additional_data":false,"paper_date":"2019-05-25","paper":"/paper/mde-multi-distance-embeddings-for-link","paper_url":"https://arxiv.org/abs/1905.10702v8","paper_title":"MDE: Multiple Distance Embeddings for Link Prediction in Knowledge Graphs","code":"https://github.com/mlwin-de/MDE","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"SimplE","metrics":{"Hits@1":"0.944","Hits@10":"0.954","Hits@3":"0.950","MR":"412","MRR":"0.948","training time (s)":"1042"},"uses_additional_data":false,"paper_date":"2019-03-02","paper":"/paper/graphvite-a-high-performance-cpu-gpu-hybrid","paper_url":"http://arxiv.org/abs/1903.00757v1","paper_title":"GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding","code":"https://github.com/DeepGraphLearning/graphvite","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"HHolE","metrics":{"Hits@1":".931","Hits@10":".951","Hits@3":".945","MR":"183","MRR":".939"},"uses_additional_data":false,"paper_date":"2018-11-02","paper":"/paper/augmenting-compositional-models-for-knowledge","paper_url":"https://arxiv.org/abs/1811.01062v2","paper_title":"Augmenting Compositional Models for Knowledge Base Completion Using Gradient Representations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"HolE","metrics":{"Hits@1":"0.930","Hits@10":"0.949","Hits@3":"0.945","MRR":"0.938"},"uses_additional_data":false,"paper_date":"2015-10-16","paper":"/paper/holographic-embeddings-of-knowledge-graphs","paper_url":"http://arxiv.org/abs/1510.04935v2","paper_title":"Holographic Embeddings of Knowledge Graphs","code":"https://github.com/Accenture/AmpliGraph","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"LogicENN","metrics":{"Hits@10":"0.948","MR":"357","MRR":"0.923"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/logicenn-a-neural-based-knowledge-graphs","paper_url":"https://arxiv.org/abs/1908.07141v1","paper_title":"LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"KBGAN (TransD + ComplEx)","metrics":{"Hits@10":"0.948","MRR":"0.779"},"uses_additional_data":false,"paper_date":"2017-11-11","paper":"/paper/kbgan-adversarial-learning-for-knowledge","paper_url":"http://arxiv.org/abs/1711.04071v3","paper_title":"KBGAN: Adversarial Learning for Knowledge Graph Embeddings","code":"https://github.com/cai-lw/KBGAN","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"ANALOGY","metrics":{"Hits@1":"0.939","Hits@10":"0.947","Hits@3":"0.944","MRR":"0.942"},"uses_additional_data":false,"paper_date":"2017-05-06","paper":"/paper/analogical-inference-for-multi-relational","paper_url":"http://arxiv.org/abs/1705.02426v2","paper_title":"Analogical Inference for Multi-Relational Embeddings","code":"https://github.com/quark0/ANALOGY","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"SimplE","metrics":{"Hits@1":"0.939","Hits@10":"0.947","Hits@3":"0.944","MRR":"0.942"},"uses_additional_data":false,"paper_date":"2018-02-13","paper":"/paper/simple-embedding-for-link-prediction-in","paper_url":"http://arxiv.org/abs/1802.04868v2","paper_title":"SimplE Embedding for Link Prediction in Knowledge Graphs","code":"https://github.com/Mehran-k/SimplE","n_code_links":2,"syntology":null},{"rank_in_archive_order":26,"model":"ComplEx","metrics":{"Hits@1":"0.936","Hits@10":"0.947","Hits@3":"0.936","MRR":"0.941"},"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":"ComplEx NSCaching","metrics":{"Hits@10":"0.9398","MR":"1072","MRR":"0.9355"},"uses_additional_data":false,"paper_date":"2018-12-16","paper":"/paper/nscaching-simple-and-efficient-negative","paper_url":"http://arxiv.org/abs/1812.06410v2","paper_title":"NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding","code":"https://github.com/yzhangee/NSCaching","n_code_links":6,"syntology":null},{"rank_in_archive_order":28,"model":"Gaifman","metrics":{"Hits@1":"0.761","Hits@10":"0.939","MR":"352"},"uses_additional_data":false,"paper_date":"2016-10-28","paper":"/paper/discriminative-gaifman-models","paper_url":"http://arxiv.org/abs/1610.09369v1","paper_title":"Discriminative Gaifman Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"DistMult","metrics":{"Hits@1":"0.728","Hits@10":"0.936","Hits@3":"0.914","MR":"902","MRR":"0.822"},"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":30,"model":"TransD","metrics":{"Hits@10":"0.922","MR":"212"},"uses_additional_data":false,"paper_date":"2015-07-01","paper":"/paper/knowledge-graph-embedding-via-dynamic-mapping","paper_url":"https://aclanthology.org/P15-1067","paper_title":"Knowledge Graph Embedding via Dynamic Mapping Matrix","code":"https://github.com/yangyucheng000/transX","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"TransE-Skipgram","metrics":{"Hits@10":"0.7987"},"uses_additional_data":false,"paper_date":"2018-09-01","paper":"/paper/auggan-cross-domain-adaptation-with-gan-based","paper_url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Sheng-Wei_Huang_AugGAN_Cross_Domain_ECCV_2018_paper.html","paper_title":"AugGAN: Cross Domain Adaptation with GAN-based Data Augmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"TransE","metrics":{"Hits@10":"0.754","MR":"263"},"uses_additional_data":false,"paper_date":"2013-12-01","paper":"/paper/translating-embeddings-for-modeling-multi","paper_url":"http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data","paper_title":"Translating Embeddings for Modeling Multi-relational Data","code":"https://github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/transe.py","n_code_links":8,"syntology":null},{"rank_in_archive_order":33,"model":"ParTransH","metrics":{"Hits@10":"0.668","MR":"215"},"uses_additional_data":false,"paper_date":"2017-03-30","paper":"/paper/efficient-parallel-translating-embedding-for","paper_url":"http://arxiv.org/abs/1703.10316v4","paper_title":"Efficient Parallel Translating Embedding For Knowledge Graphs","code":"https://github.com/zdh2292390/ParTrans-X","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"DistMult (after variational EM)","metrics":{"MRR":"0.911"},"uses_additional_data":false,"paper_date":"2019-07-01","paper":"/paper/augmenting-and-tuning-knowledge-graph","paper_url":"https://arxiv.org/abs/1907.01068v1","paper_title":"Augmenting and Tuning Knowledge Graph Embeddings","code":"https://github.com/mandt-lab/knowledge-graph-tuning","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":35,"model":"GraphVite (zhu2019graphvite)","metrics":{"training time (s)":"6"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/pykeen-1-0-a-python-library-for-training-and","paper_url":"https://arxiv.org/abs/2007.14175v2","paper_title":"PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings","code":"https://github.com/pykeen/pykeen","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"LibKGE (ruffinelli2020you)","metrics":{"training time (s)":"10"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/pykeen-1-0-a-python-library-for-training-and","paper_url":"https://arxiv.org/abs/2007.14175v2","paper_title":"PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings","code":"https://github.com/pykeen/pykeen","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"OpenKE (han2018openke)","metrics":{"training time (s)":"11"},"uses_additional_data":false,"paper_date":"2020-07-28","paper":"/paper/pykeen-1-0-a-python-library-for-training-and","paper_url":"https://arxiv.org/abs/2007.14175v2","paper_title":"PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings","code":"https://github.com/pykeen/pykeen","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+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":1,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":35,"n_samples":37,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":50,"n_samples":52,"n_pointer_only_licence":2,"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"}}}