{"url":"/sota/link-prediction-on-fb15k-237","task":{"name":"Link Prediction","url":"/task/link-prediction","note":null},"dataset":{"name":"FB15k-237","url":"/dataset/fb15k-237"},"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","training time (s)","Hit@1","Hit@10"],"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,"training time (s)":"lower","Hit@1":null,"Hit@10":null}},"counts":{"rows":75,"rows_with_code":67,"rows_with_paper_page":75,"rows_dated":75,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"NBFNet","metrics":{"Hits@1":"0.321","Hits@10":"0.599","Hits@3":"0.454","MR":"114","MRR":"0.415"},"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":2,"n_unverified":13,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"KG-R3 (this work)","metrics":{"Hits@1":"0.315","Hits@3":"0.413","MRR":"0.39"},"uses_additional_data":false,"paper_date":"2022-12-19","paper":"/paper/a-retrieve-and-read-framework-for-knowledge","paper_url":"https://arxiv.org/abs/2212.09724v3","paper_title":"A Retrieve-and-Read Framework for Knowledge Graph Link Prediction","code":"https://github.com/OSU-NLP-Group/KG-R3","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Relphormer","metrics":{"Hits@1":"0.314","Hits@10":"0.481","MRR":"0.371"},"uses_additional_data":false,"paper_date":"2022-05-22","paper":"/paper/relphormer-relational-graph-transformer-for","paper_url":"https://arxiv.org/abs/2205.10852v6","paper_title":"Relphormer: Relational Graph Transformer for Knowledge Graph Representations","code":"https://github.com/zjunlp/relphormer","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MetaSD","metrics":{"Hits@1":"0.300","Hits@10":"0.571","Hits@3":"0.428","MRR":"0.391"},"uses_additional_data":false,"paper_date":"2023-05-20","paper":"/paper/self-distillation-with-meta-learning-for-1","paper_url":"https://arxiv.org/abs/2305.12209v1","paper_title":"Self-Distillation with Meta Learning for Knowledge Graph Completion","code":"https://github.com/pldlgb/MetaSD","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"ComplEx-N3-RP","metrics":{"Hits@1":"0.298","Hits@10":"0.568","Hits@3":"0.424","MR":"163","MRR":"0.389"},"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":6,"model":"SAFRAN","metrics":{"Hits@1":"0.298","Hits@10":"0.537","MRR":"0.389"},"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":7,"model":"MoCoKGC","metrics":{"Hits@1":"0.296","Hits@10":"0.580","Hits@3":"0.431","MRR":"0.391"},"uses_additional_data":false,"paper_date":"2024-11-12","paper":"/paper/mocokgc-momentum-contrast-entity-encoding-for","paper_url":"https://aclanthology.org/2024.emnlp-main.832/","paper_title":"MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"MoCoSA","metrics":{"Hits@1":"0.292","Hits@10":"0.578","Hits@3":"0.42","MRR":"0.387"},"uses_additional_data":false,"paper_date":"2023-08-16","paper":"/paper/mocosa-momentum-contrast-for-knowledge-graph","paper_url":"https://arxiv.org/abs/2308.08204v1","paper_title":"MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented Pre-trained Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"kNN-KGE","metrics":{"Hits@1":"0.280","Hits@10":"0.550","Hits@3":"0.404","MR":"185","MRR":"0.370"},"uses_additional_data":true,"paper_date":"2022-01-14","paper":"/paper/reasoning-through-memorization-nearest","paper_url":"https://arxiv.org/abs/2201.05575v4","paper_title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","code":"https://github.com/zjunlp/knn-kg","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"ComplEx-DURA","metrics":{"Hits@1":"0.276","Hits@10":"0.560","MRR":"0.371"},"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":11,"model":"MEIM","metrics":{"Hits@1":"0.274","Hits@10":"0.557","Hits@3":"0.406","MRR":"0.369"},"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":12,"model":"NePTuNe","metrics":{"Hits@1":"0.272","Hits@10":"0.547","Hits@3":"0.404","MRR":"0.366"},"uses_additional_data":false,"paper_date":"2021-04-15","paper":"/paper/neptune-neural-powered-tucker-network-for","paper_url":"https://arxiv.org/abs/2104.07824v1","paper_title":"NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion","code":"https://github.com/luffycodes/neptune","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"MEI","metrics":{"Hits@1":"0.271","Hits@10":"0.552","Hits@3":"0.402","MRR":"0.365"},"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":"SE-GNN (ours)","metrics":{"Hits@1":"0.271","Hits@10":"0.549","Hits@3":"0.399","MR":"157","MRR":"0.365"},"uses_additional_data":false,"paper_date":"2021-09-24","paper":"/paper/how-does-knowledge-graph-embedding","paper_url":"https://arxiv.org/abs/2109.11800v3","paper_title":"How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View","code":"https://github.com/renli1024/se-gnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"RESCAL (SCE w/ LS pretrained)","metrics":{"Hits@1":"0.269","Hits@10":"0.55","Hits@3":"0.402","MRR":"0.364"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/unified-interpretation-of-softmax-cross","paper_url":"https://arxiv.org/abs/2106.07250v4","paper_title":"Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding","code":"https://github.com/kamigaito/acl2021kge","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"RESCAL (SCE w/ LS)","metrics":{"Hits@1":"0.269","Hits@10":"0.548","Hits@3":"0.4","MRR":"0.363"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/unified-interpretation-of-softmax-cross","paper_url":"https://arxiv.org/abs/2106.07250v4","paper_title":"Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding","code":"https://github.com/kamigaito/acl2021kge","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"QuatDE","metrics":{"Hits@1":"0.268","Hits@10":"0.563","Hits@3":"0.40","MR":"90","MRR":"0.365"},"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":18,"model":"SAttLE","metrics":{"Hits@1":"0.268","Hits@10":"0.545","Hits@3":"0.396","MRR":"0.36"},"uses_additional_data":false,"paper_date":"2021-12-20","paper":"/paper/self-attention-presents-low-dimensional","paper_url":"https://arxiv.org/abs/2112.10644v3","paper_title":"Self-attention Presents Low-dimensional Knowledge Graph Embeddings for Link Prediction","code":"https://github.com/peyman-bi/sattle","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"GC-OTE","metrics":{"Hits@1":"0.267","Hits@10":"0.550","Hits@3":"0.396","MR":"154","MRR":"0.361"},"uses_additional_data":false,"paper_date":"2019-11-09","paper":"/paper/orthogonal-relation-transforms-with-graph","paper_url":"https://arxiv.org/abs/1911.04910v3","paper_title":"Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"StAR","metrics":{"Hits@1":"0.266","Hits@10":"0.562","Hits@3":"0.404","MR":"117","MRR":"0.365"},"uses_additional_data":true,"paper_date":"2020-04-30","paper":"/paper/semantic-triple-encoder-for-fast-open-set","paper_url":"https://arxiv.org/abs/2004.14781v2","paper_title":"Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion","code":"https://github.com/wangbo9719/StAR_KGC","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"KERMIT","metrics":{"Hits@1":"0.266","Hits@10":"0.547","Hits@3":"0.396","MRR":"0.359"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/kermit-knowledge-graph-completion-of-enhanced","paper_url":"https://arxiv.org/abs/2309.14770v2","paper_title":"KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation","code":"https://github.com/lirt1231/kermit","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"TuckER","metrics":{"Hits@1":"0.266","Hits@10":"0.544","Hits@3":"0.394","MRR":"0.358"},"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":23,"model":"RotatE + GreenKGC (Ours)","metrics":{"Hits@1":"0.265","Hits@10":"0.507","Hits@3":"0.369","MRR":"0.345"},"uses_additional_data":false,"paper_date":"2022-08-19","paper":"/paper/greenkgc-a-lightweight-knowledge-graph","paper_url":"https://arxiv.org/abs/2208.09137v2","paper_title":"GreenKGC: A Lightweight Knowledge Graph Completion Method","code":"https://github.com/yunchengwang/greenkgc","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"LineaRE","metrics":{"Hits@1":"0.264","Hits@10":"0.545","Hits@3":"0.391","MR":"155","MRR":"0.357"},"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":25,"model":"CompGCN","metrics":{"Hits@1":"0.264","Hits@10":"0.535","Hits@3":"0.390","MR":"197","MRR":"0.355"},"uses_additional_data":false,"paper_date":"2019-11-08","paper":"/paper/composition-based-multi-relational-graph","paper_url":"https://arxiv.org/abs/1911.03082v2","paper_title":"Composition-based Multi-Relational Graph Convolutional Networks","code":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/compGCN","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":26,"model":"TuckER-RP","metrics":{"Hits@1":"0.264","Hits@10":"0.535","Hits@3":"0.388","MRR":"0.354"},"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":27,"model":"InteractE","metrics":{"Hits@1":"0.263","Hits@10":"0.535","MR":"172","MRR":"0.354"},"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":28,"model":"RESCAL + Decom","metrics":{"Hits@1":"0.261","Hits@10":"0.536","Hits@3":"0.388","MRR":"0.354"},"uses_additional_data":false,"paper_date":"2019-11-11","paper":"/paper/decompressing-knowledge-graph-representations","paper_url":"https://arxiv.org/abs/1911.04053v2","paper_title":"Decompressing Knowledge Graph Representations for Link Prediction","code":"https://github.com/shawnkx/Decom","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"ConvR","metrics":{"Hits@1":"0.261","Hits@10":"0.528","Hits@3":"0.385","MRR":"0.350"},"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":30,"model":"Structure-Aware Convolutional Networks","metrics":{"Hits@1":"0.26","Hits@10":"0.54","Hits@3":"0.39","MRR":"0.35"},"uses_additional_data":false,"paper_date":"2018-11-11","paper":"/paper/end-to-end-structure-aware-convolutional","paper_url":"http://arxiv.org/abs/1811.04441v2","paper_title":"End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion","code":"https://github.com/JD-AI-Research-Silicon-Valley/SACN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"RefE","metrics":{"Hits@1":"0.256","Hits@10":"0.541","Hits@3":"0.390","MRR":"0.351"},"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":32,"model":"DensE","metrics":{"Hits@1":"0.256","Hits@10":"0.535","Hits@3":"0.384","MR":"169","MRR":"0.349"},"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":33,"model":"DRUM (T=3)","metrics":{"Hits@1":"0.255","Hits@10":"0.516","Hits@3":"0.378","MRR":"0.343"},"uses_additional_data":false,"paper_date":"2019-10-31","paper":"/paper/drum-end-to-end-differentiable-rule-mining-on","paper_url":"https://arxiv.org/abs/1911.00055v1","paper_title":"DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs","code":"https://github.com/alisadeghian/DRUM","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"HypER","metrics":{"Hits@1":"0.252","Hits@10":"0.520","Hits@3":"0.376","MRR":"0.341"},"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":35,"model":"TransE + GreenKGC (Ours)","metrics":{"Hits@1":"0.251","Hits@10":"0.493","Hits@3":"0.356","MRR":"0.331"},"uses_additional_data":false,"paper_date":"2022-08-19","paper":"/paper/greenkgc-a-lightweight-knowledge-graph","paper_url":"https://arxiv.org/abs/2208.09137v2","paper_title":"GreenKGC: A Lightweight Knowledge Graph Completion Method","code":"https://github.com/yunchengwang/greenkgc","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"HAKE","metrics":{"Hits@1":"0.25","Hits@3":"0.381","MRR":"0.346"},"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":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":1}},{"rank_in_archive_order":37,"model":"SimKGCIB(+PB+SN)","metrics":{"Hits@1":"0.249","Hits@10":"0.511","Hits@3":"0.365","MRR":"0.336"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/simkgc-simple-contrastive-knowledge-graph","paper_url":"https://arxiv.org/abs/2203.02167v1","paper_title":"SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models","code":"https://github.com/intfloat/simkgc","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":3}},{"rank_in_archive_order":38,"model":"QuatE","metrics":{"Hits@1":"0.248","Hits@10":"0.550","Hits@3":"0.382","MR":"87","MRR":"0.348"},"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":39,"model":"DaBR","metrics":{"Hits@1":"0.247","Hits@10":"0.572","Hits@3":"0.410","MR":"83","MRR":"0.373"},"uses_additional_data":false,"paper_date":"2024-12-05","paper":"/paper/distance-adaptive-quaternion-knowledge-graph","paper_url":"https://arxiv.org/abs/2412.04076v2","paper_title":"Distance-Adaptive Quaternion Knowledge Graph Embedding with Bidirectional Rotation","code":"https://github.com/llqy123/dabr","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"ConE","metrics":{"Hits@1":"0.247","Hits@10":"0.54","Hits@3":"0.381","MRR":"0.345"},"uses_additional_data":false,"paper_date":"2021-10-28","paper":"/paper/modeling-heterogeneous-hierarchies-with","paper_url":"https://arxiv.org/abs/2110.14923v2","paper_title":"Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones","code":"https://github.com/snap-stanford/ConE","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"Rot-Pro","metrics":{"Hits@1":"0.246","Hits@10":"0.540","Hits@3":"0.383","MRR":"0.344"},"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":42,"model":"MuRP","metrics":{"Hits@1":"0.245","Hits@10":"0.521","Hits@3":"0.370","MRR":"0.336"},"uses_additional_data":false,"paper_date":"2019-05-23","paper":"/paper/multi-relational-poincare-graph-embeddings","paper_url":"https://arxiv.org/abs/1905.09791v3","paper_title":"Multi-relational Poincaré Graph Embeddings","code":"https://github.com/ibalazevic/multirelational-poincare","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"RotatE","metrics":{"Hits@1":"0.241","Hits@10":"0.533","Hits@3":"0.375","MR":"177","MRR":"0.338"},"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":44,"model":"BoxE","metrics":{"Hits@1":"0.238","Hits@10":"0.538","MRR":"0.337"},"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":45,"model":"ConvE","metrics":{"Hits@1":"0.237","Hits@10":"0.501","Hits@3":"0.356","MRR":"0.325"},"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":46,"model":"pRotatE","metrics":{"Hits@1":"0.23","Hits@10":"0.524","Hits@3":"0.365","MR":"178","MRR":"0.328"},"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":47,"model":"LP-BERT","metrics":{"Hits@1":"0.223","Hits@10":"0.490","Hits@3":"0.336","MR":"154","MRR":"0.31"},"uses_additional_data":true,"paper_date":"2022-01-13","paper":"/paper/lp-bert-multi-task-pre-training-knowledge","paper_url":"https://arxiv.org/abs/2201.04843v2","paper_title":"Multi-task Pre-training Language Model for Semantic Network Completion","code":"https://github.com/763337092/LP-BERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"RotatE","metrics":{"Hits@1":"0.217","Hits@10":"0.511","Hits@3":"0.347","MR":"176","MRR":"0.314","training time (s)":"857"},"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":49,"model":"KGLM","metrics":{"Hits@1":"0.200","Hits@10":"0.468","Hits@3":"0.314","MR":"125.9","MRR":".289"},"uses_additional_data":false,"paper_date":"2022-11-04","paper":"/paper/kglm-integrating-knowledge-graph-structure-in","paper_url":"https://arxiv.org/abs/2211.02744v2","paper_title":"KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction","code":"https://github.com/ibpa/kglm","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"JoBi ComplEx","metrics":{"Hits@1":"0.199","Hits@10":"0.479","Hits@3":"0.319","MRR":"0.29"},"uses_additional_data":false,"paper_date":"2019-10-25","paper":"/paper/using-pairwise-occurrence-information-to","paper_url":"https://arxiv.org/abs/1910.11583v1","paper_title":"Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":51,"model":"TransE","metrics":{"Hits@1":"0.1987","Hits@10":".4709","MRR":"0.2904"},"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":52,"model":"GenKGC","metrics":{"Hits@1":"0.192","Hits@10":"0.439","Hits@3":"0.355"},"uses_additional_data":false,"paper_date":"2022-02-04","paper":"/paper/from-discrimination-to-generation-knowledge","paper_url":"https://arxiv.org/abs/2202.02113v7","paper_title":"From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer","code":"https://github.com/zjunlp/PromptKG/tree/main/research/GenKGC","n_code_links":1,"syntology":null},{"rank_in_archive_order":53,"model":"MLMLM","metrics":{"Hits@1":"0.1871","Hits@10":"0.4026","Hits@3":"0.2820","MR":"411","MRR":"0.2591"},"uses_additional_data":false,"paper_date":"2020-09-15","paper":"/paper/mlmlm-link-prediction-with-mean-likelihood","paper_url":"https://arxiv.org/abs/2009.07058v1","paper_title":"MLMLM: Link Prediction with Mean Likelihood Masked Language Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":54,"model":"RR-GCN-PPV","metrics":{"Hits@1":"0.157","Hits@10":"0.412","Hits@3":"0.256","MRR":"0.238"},"uses_additional_data":false,"paper_date":"2022-03-04","paper":"/paper/r-gcn-the-r-could-stand-for-random","paper_url":"https://arxiv.org/abs/2203.02424v2","paper_title":"R-GCN: The R Could Stand for Random","code":"https://github.com/predict-idlab/RR-GCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"TransD","metrics":{"Hits@1":"0.1483","Hits@10":"0.4605","MRR":"0.2527"},"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":56,"model":"Inverse Model","metrics":{"Hits@1":"0.007","Hits@10":"0.014","Hits@3":"0.011","MR":"7030","MRR":"0.010"},"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":57,"model":"HittER","metrics":{"Hit@1":"0.279","Hit@10":"0.558","Hits@3":"0.409","MRR":"0.373"},"uses_additional_data":false,"paper_date":"2020-08-28","paper":"/paper/hitter-hierarchical-transformers-for","paper_url":"https://arxiv.org/abs/2008.12813v2","paper_title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","code":"https://github.com/zjunlp/relphormer","n_code_links":3,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":58,"model":"AutoKGE","metrics":{"Hits@10":"0.555","MRR":"0.365"},"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":59,"model":"CP-N3-RP","metrics":{"Hits@10":"0.55","MRR":"0.366"},"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":60,"model":"DistMult (after variational EM)","metrics":{"Hits@10":"0.548","MRR":"0.357"},"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":61,"model":"KG-R3","metrics":{"Hits@10":"0.539"},"uses_additional_data":false,"paper_date":"2022-12-19","paper":"/paper/a-retrieve-and-read-framework-for-knowledge","paper_url":"https://arxiv.org/abs/2212.09724v3","paper_title":"A Retrieve-and-Read Framework for Knowledge Graph Link Prediction","code":"https://github.com/OSU-NLP-Group/KG-R3","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"LASS","metrics":{"Hits@10":"0.533","MR":"108"},"uses_additional_data":false,"paper_date":"2022-09-19","paper":"/paper/joint-language-semantic-and-structure","paper_url":"https://arxiv.org/abs/2209.08721v1","paper_title":"Joint Language Semantic and Structure Embedding for Knowledge Graph Completion","code":"https://github.com/pkusjh/lass","n_code_links":1,"syntology":null},{"rank_in_archive_order":63,"model":"MDE_adv","metrics":{"Hits@10":"0.531","MR":"203","MRR":"0.344"},"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":64,"model":"GFA-NN","metrics":{"Hits@10":"0.522","MR":"186","MRR":"0.338"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/embedding-knowledge-graphs-attentive-to","paper_url":"https://2021.ecmlpkdd.org/wp-content/uploads/2021/07/sub_1096.pdf","paper_title":"Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities","code":"https://github.com/afshinsadeghi/GFA-NN","n_code_links":1,"syntology":null},{"rank_in_archive_order":65,"model":"KGRefiner","metrics":{"Hits@10":"0.489","MR":"203","MRR":"0.302","training time (s)":"1100"},"uses_additional_data":false,"paper_date":"2021-06-27","paper":"/paper/kgrefiner-knowledge-graph-refinement-for","paper_url":"https://arxiv.org/abs/2106.14233v2","paper_title":"KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":66,"model":"ComplEx NSCaching","metrics":{"Hits@10":"0.4805","MR":"221","MRR":"0.3021"},"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":67,"model":"LogicENN","metrics":{"Hits@10":"0.473","MR":"424"},"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":68,"model":"KBGAN (TransD + ComplEx)","metrics":{"Hits@10":"0.458","MRR":"0.277"},"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":69,"model":"PALT","metrics":{"Hits@10":"0.444","MR":"144"},"uses_additional_data":false,"paper_date":"2022-10-25","paper":"/paper/palt-parameter-lite-transfer-of-language","paper_url":"https://arxiv.org/abs/2210.13715v1","paper_title":"PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion","code":"https://github.com/yuanyehome/palt","n_code_links":1,"syntology":null},{"rank_in_archive_order":70,"model":"ComplEx","metrics":{"Hits@10":"0.428"},"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":71,"model":"ConvKB (Corrected)","metrics":{"Hits@10":".421","MR":"309","MRR":".309"},"uses_additional_data":false,"paper_date":"2019-11-10","paper":"/paper/a-re-evaluation-of-knowledge-graph-completion","paper_url":"https://arxiv.org/abs/1911.03903v3","paper_title":"A Re-evaluation of Knowledge Graph Completion Methods","code":"https://github.com/daiquocnguyen/ConvKB","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":72,"model":"KG-BERT","metrics":{"Hits@10":"0.42","MR":"153"},"uses_additional_data":false,"paper_date":"2019-09-07","paper":"/paper/kg-bert-bert-for-knowledge-graph-completion","paper_url":"https://arxiv.org/abs/1909.03193v2","paper_title":"KG-BERT: BERT for Knowledge Graph Completion","code":"https://github.com/yao8839836/kg-bert","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":73,"model":"DistMult","metrics":{"Hits@10":"0.419","MRR":"0.241"},"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":74,"model":"KBAT (Corrected)","metrics":{"Hits@10":".331","MR":"270","MRR":".157"},"uses_additional_data":false,"paper_date":"2019-11-10","paper":"/paper/a-re-evaluation-of-knowledge-graph-completion","paper_url":"https://arxiv.org/abs/1911.03903v3","paper_title":"A Re-evaluation of Knowledge Graph Completion Methods","code":"https://github.com/daiquocnguyen/ConvKB","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":75,"model":"CapsE (Corrected)","metrics":{"Hits@10":".057","MR":"446","MRR":".032"},"uses_additional_data":false,"paper_date":"2019-11-10","paper":"/paper/a-re-evaluation-of-knowledge-graph-completion","paper_url":"https://arxiv.org/abs/1911.03903v3","paper_title":"A Re-evaluation of Knowledge Graph Completion Methods","code":"https://github.com/daiquocnguyen/ConvKB","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":7,"n_samples":7,"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 6,795 of the 9,581 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":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":23,"rows_with_any_sample_ran":9,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":27,"n_unverified":89,"n_samples":116,"n_pointer_only_licence":26,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":27,"n_unverified":108,"n_samples":135,"n_pointer_only_licence":26,"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"}}}