{"url":"/task/link-prediction","name":"Link Prediction","slug":"link-prediction","description_markdown":"**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>","categories":[{"name":"Graphs","url":"/area/graphs"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1949,"papers_with_code":974,"benchmarks":80,"benchmark_tables_in_archive":80,"benchmark_tables_shown":80,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":67,"subtasks":6,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/link-prediction-on-fb15k-237","slug":"link-prediction-on-fb15k-237","dataset":"FB15k-237","dataset_url":"/dataset/fb15k-237","rows_in_archive":75,"metrics":["Hits@1","Hits@3","Hits@10","MRR","MR","training time (s)","Hit@1","Hit@10"],"first_row_in_archive_order":{"model":"NBFNet","paper_title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","paper_url":"/paper/neural-bellman-ford-networks-a-general-graph","paper_date":"2021-06-13","arxiv_id":"2106.06935","code_links":[{"title":"DeepGraphLearning/NBFNet","url":"https://github.com/DeepGraphLearning/NBFNet"},{"title":"fs302/EasyLink","url":"https://github.com/fs302/EasyLink/blob/main/example/ogbl_ppa_ra.py"},{"title":"fs302/EasyLink","url":"https://github.com/fs302/EasyLink"}],"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-wn18rr","slug":"link-prediction-on-wn18rr","dataset":"WN18RR","dataset_url":"/dataset/wn18rr","rows_in_archive":75,"metrics":["Hits@10","Hits@3","Hits@1","MRR","MR"],"first_row_in_archive_order":{"model":"MoCoKGC","paper_title":"MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion","paper_url":"/paper/mocokgc-momentum-contrast-entity-encoding-for","paper_date":"2024-11-12","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-wn18","slug":"link-prediction-on-wn18","dataset":"WN18","dataset_url":"/dataset/wn18","rows_in_archive":37,"metrics":["Hits@10","Hits@3","Hits@1","MRR","MR","training time (s)"],"first_row_in_archive_order":{"model":"Inverse Model","paper_title":"Convolutional 2D Knowledge Graph Embeddings","paper_url":"/paper/convolutional-2d-knowledge-graph-embeddings","paper_date":"2017-07-05","arxiv_id":"1707.01476","code_links":[{"title":"TimDettmers/ConvE","url":"https://github.com/TimDettmers/ConvE"},{"title":"INK-USC/RE-Net","url":"https://github.com/INK-USC/RE-Net"},{"title":"thu-keg/eakit","url":"https://github.com/thu-keg/eakit"},{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"},{"title":"bi-graph/emgraph","url":"https://github.com/bi-graph/emgraph"},{"title":"uma-pi1/kge-iclr20","url":"https://github.com/uma-pi1/kge-iclr20"},{"title":"LB0828/conve_reproduce","url":"https://github.com/LB0828/conve_reproduce"},{"title":"oliver-lloyd/kge_param_sens","url":"https://github.com/oliver-lloyd/kge_param_sens"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb15k","slug":"link-prediction-on-fb15k","dataset":"FB15k","dataset_url":"/dataset/fb15k","rows_in_archive":23,"metrics":["MRR","Hits@1","Hits@3","Hits@10","MR","training time (s)"],"first_row_in_archive_order":{"model":"AutoKGE","paper_title":"AutoSF: Searching Scoring Functions for Knowledge Graph Embedding","paper_url":"/paper/autokge-searching-scoring-functions-for","paper_date":"2019-04-26","arxiv_id":"1904.11682","code_links":[{"title":"AutoML-4Paradigm/ERAS","url":"https://github.com/AutoML-4Paradigm/ERAS"},{"title":"AutoML-4Paradigm/S2S","url":"https://github.com/AutoML-4Paradigm/S2S"},{"title":"AutoML-Research/S2S","url":"https://github.com/AutoML-Research/S2S"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-pcqm-contact","slug":"link-prediction-on-pcqm-contact","dataset":"PCQM-Contact","dataset_url":"/dataset/pascalvoc-sp","rows_in_archive":18,"metrics":["Hits@1","Hits@3","Hits@10","MRR","MRR-ext-filtered"],"first_row_in_archive_order":{"model":"ViT-PS","paper_title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","paper_url":"/paper/learning-probabilistic-symmetrization-for-1","paper_date":"2023-06-05","arxiv_id":"2306.02866","code_links":[{"title":"jw9730/lps","url":"https://github.com/jw9730/lps"}],"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-yago3-10","slug":"link-prediction-on-yago3-10","dataset":"YAGO3-10","dataset_url":"/dataset/yago3-10","rows_in_archive":18,"metrics":["Hits@1","Hits@3","Hits@10","MRR","MR"],"first_row_in_archive_order":{"model":"MEIM","paper_title":"MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction","paper_url":"/paper/meim-multi-partition-embedding-interaction","paper_date":"2022-09-30","arxiv_id":"2209.15597","code_links":[{"title":"tranhungnghiep/AnalyzingKGEmbeddings","url":"https://github.com/tranhungnghiep/AnalyzingKGEmbeddings"},{"title":"tranhungnghiep/AnalyzeKGE","url":"https://github.com/tranhungnghiep/AnalyzeKGE"},{"title":"tranhungnghiep/meim-kge","url":"https://github.com/tranhungnghiep/meim-kge"},{"title":"tranhungnghiep/MEI-KGE","url":"https://github.com/tranhungnghiep/MEI-KGE"}],"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}}},{"leaderboard":"/sota/link-prediction-on-icews05-15-1","slug":"link-prediction-on-icews05-15-1","dataset":"ICEWS05-15","dataset_url":"/dataset/icews","rows_in_archive":16,"metrics":["MRR"],"first_row_in_archive_order":{"model":"SPA","paper_title":"Search to Pass Messages for Temporal Knowledge Graph Completion","paper_url":"/paper/search-to-pass-messages-for-temporal","paper_date":"2022-10-30","arxiv_id":"2210.16740","code_links":[{"title":"striderdu/spa","url":"https://github.com/striderdu/spa"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-icews14-1","slug":"link-prediction-on-icews14-1","dataset":"ICEWS14","dataset_url":"/dataset/icews","rows_in_archive":16,"metrics":["MRR"],"first_row_in_archive_order":{"model":"SPA","paper_title":"Search to Pass Messages for Temporal Knowledge Graph Completion","paper_url":"/paper/search-to-pass-messages-for-temporal","paper_date":"2022-10-30","arxiv_id":"2210.16740","code_links":[{"title":"striderdu/spa","url":"https://github.com/striderdu/spa"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-wikidata5m","slug":"link-prediction-on-wikidata5m","dataset":"Wikidata5M","dataset_url":"/dataset/wikidata5m","rows_in_archive":14,"metrics":["MRR","Hits@10","Hits@1","Hits@3"],"first_row_in_archive_order":{"model":"MoCoKGC","paper_title":"MoCoKGC: Momentum Contrast Entity Encoding for Knowledge Graph Completion","paper_url":"/paper/mocokgc-momentum-contrast-entity-encoding-for","paper_date":"2024-11-12","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-citeseer","slug":"link-prediction-on-citeseer","dataset":"Citeseer","dataset_url":"/dataset/citeseer","rows_in_archive":13,"metrics":["AUC","AP","Accuracy","ACC"],"first_row_in_archive_order":{"model":"NESS","paper_title":"NESS: Node Embeddings from Static SubGraphs","paper_url":"/paper/ness-learning-node-embeddings-from-static","paper_date":"2023-03-15","arxiv_id":"2303.08958","code_links":[{"title":"AstraZeneca/NESS","url":"https://github.com/AstraZeneca/NESS"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-cora","slug":"link-prediction-on-cora","dataset":"Cora","dataset_url":"/dataset/cora","rows_in_archive":13,"metrics":["AUC","AP","Accuracy","ACC"],"first_row_in_archive_order":{"model":"NESS","paper_title":"NESS: Node Embeddings from Static SubGraphs","paper_url":"/paper/ness-learning-node-embeddings-from-static","paper_date":"2023-03-15","arxiv_id":"2303.08958","code_links":[{"title":"AstraZeneca/NESS","url":"https://github.com/AstraZeneca/NESS"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-pubmed","slug":"link-prediction-on-pubmed","dataset":"Pubmed","dataset_url":"/dataset/pubmed","rows_in_archive":13,"metrics":["AUC","AP","Accuracy","ACC"],"first_row_in_archive_order":{"model":null,"paper_title":"An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022","paper_url":"/paper/an-effective-graph-learning-based-approach","paper_date":"2022-03-01","arxiv_id":"2203.01820","code_links":[{"title":"im0qianqian/WSDM2022TGP-AntGraph","url":"https://github.com/im0qianqian/WSDM2022TGP-AntGraph"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-gdelt","slug":"link-prediction-on-gdelt","dataset":"GDELT","dataset_url":"/dataset/gdelt","rows_in_archive":11,"metrics":["MRR"],"first_row_in_archive_order":{"model":"SPA","paper_title":"Search to Pass Messages for Temporal Knowledge Graph Completion","paper_url":"/paper/search-to-pass-messages-for-temporal","paper_date":"2022-10-30","arxiv_id":"2210.16740","code_links":[{"title":"striderdu/spa","url":"https://github.com/striderdu/spa"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb15k-1","slug":"link-prediction-on-fb15k-1","dataset":"FB15k","dataset_url":"/dataset/fb15k","rows_in_archive":10,"metrics":["MRR","Hits@1","Hits@3","Hits@10","MR","MRR raw","Hits@5"],"first_row_in_archive_order":{"model":"ComplEx-N3 (reciprocal)","paper_title":"Canonical Tensor Decomposition for Knowledge Base Completion","paper_url":"/paper/canonical-tensor-decomposition-for-knowledge","paper_date":"2018-06-19","arxiv_id":"1806.07297","code_links":[{"title":"facebookresearch/kbc","url":"https://github.com/facebookresearch/kbc"},{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"},{"title":"twktheainur/kbc","url":"https://github.com/twktheainur/kbc"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/link-prediction-on-umls","slug":"link-prediction-on-umls","dataset":"UMLS","dataset_url":"/dataset/umls","rows_in_archive":10,"metrics":["Hits@10","MR"],"first_row_in_archive_order":{"model":"LP-BERT","paper_title":"Multi-task Pre-training Language Model for Semantic Network Completion","paper_url":"/paper/lp-bert-multi-task-pre-training-knowledge","paper_date":"2022-01-13","arxiv_id":"2201.04843","code_links":[{"title":"763337092/LP-BERT","url":"https://github.com/763337092/LP-BERT"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-yelp","slug":"link-prediction-on-yelp","dataset":"Yelp","dataset_url":"/dataset/yelp","rows_in_archive":9,"metrics":["HR@10","AUC","nDCG@10"],"first_row_in_archive_order":{"model":"PEAGAT","paper_title":"Metapath- and Entity-aware Graph Neural Network for Recommendation","paper_url":"/paper/metapath-and-entity-aware-graph-neural","paper_date":"2020-10-22","arxiv_id":"2010.11793","code_links":[{"title":"ecml-peagnn/PEAGNN","url":"https://github.com/ecml-peagnn/PEAGNN"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-openbiolink","slug":"link-prediction-on-openbiolink","dataset":"OpenBioLink","dataset_url":null,"rows_in_archive":8,"metrics":["Hits@10","Interpretable"],"first_row_in_archive_order":{"model":"DistMult","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-codex-medium","slug":"link-prediction-on-codex-medium","dataset":"CoDEx Medium","dataset_url":"/dataset/codex-medium","rows_in_archive":7,"metrics":["MRR","Hits@1","Hits@3","Hits@10"],"first_row_in_archive_order":{"model":"ULTRA","paper_title":"Towards Foundation Models for Knowledge Graph Reasoning","paper_url":"/paper/towards-foundation-models-for-knowledge-graph","paper_date":"2023-10-06","arxiv_id":"2310.04562","code_links":[{"title":"DeepGraphLearning/ULTRA","url":"https://github.com/DeepGraphLearning/ULTRA"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-movielens-25m","slug":"link-prediction-on-movielens-25m","dataset":"MovieLens 25M","dataset_url":"/dataset/movielens","rows_in_archive":7,"metrics":["nDCG@10","Hits@10"],"first_row_in_archive_order":{"model":"PEAGAT","paper_title":"Metapath- and Entity-aware Graph Neural Network for Recommendation","paper_url":"/paper/metapath-and-entity-aware-graph-neural","paper_date":"2020-10-22","arxiv_id":"2010.11793","code_links":[{"title":"ecml-peagnn/PEAGNN","url":"https://github.com/ecml-peagnn/PEAGNN"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-wordnet","slug":"link-prediction-on-wordnet","dataset":"WordNet","dataset_url":null,"rows_in_archive":7,"metrics":["Accuracy","AUC","AUPR"],"first_row_in_archive_order":{"model":"Hyperbolic Entailment Cones","paper_title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","paper_url":"/paper/hyperbolic-entailment-cones-for-learning","paper_date":"2018-04-03","arxiv_id":"1804.01882","code_links":[{"title":"dalab/hyperbolic_cones","url":"https://github.com/dalab/hyperbolic_cones"},{"title":"dinobby/hypemo","url":"https://github.com/dinobby/hypemo"},{"title":"iesl/geometric_graph_embedding","url":"https://github.com/iesl/geometric_graph_embedding"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-codex","slug":"link-prediction-on-codex","dataset":"CoDEx Small","dataset_url":"/dataset/codex","rows_in_archive":6,"metrics":["MRR","Hits@1","Hits@3","Hits@10"],"first_row_in_archive_order":{"model":"ComplEx-N3-RP","paper_title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","paper_url":"/paper/relation-prediction-as-an-auxiliary-training","paper_date":"2021-10-06","arxiv_id":"2110.02834","code_links":[{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-codex-large","slug":"link-prediction-on-codex-large","dataset":"CoDEx Large","dataset_url":"/dataset/codex-large","rows_in_archive":6,"metrics":["MRR","Hits@1","Hits@3","Hits@10"],"first_row_in_archive_order":{"model":"ComplEx-N3-RP","paper_title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","paper_url":"/paper/relation-prediction-as-an-auxiliary-training","paper_date":"2021-10-06","arxiv_id":"2110.02834","code_links":[{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb122","slug":"link-prediction-on-fb122","dataset":"FB122","dataset_url":"/dataset/fb122","rows_in_archive":5,"metrics":["HITS@3","Hits@5","Hits@10","MRR"],"first_row_in_archive_order":{"model":"Prob-CBR","paper_title":"Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion","paper_url":"/paper/probabilistic-case-based-reasoning-for-open","paper_date":"2020-10-07","arxiv_id":"2010.03548","code_links":[{"title":"ameyagodbole/Prob-CBR","url":"https://github.com/ameyagodbole/Prob-CBR"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-nell-995","slug":"link-prediction-on-nell-995","dataset":"NELL-995","dataset_url":"/dataset/nell-995","rows_in_archive":4,"metrics":["Hits@1","Hits@10","MRR","Mean AP","HITS@3"],"first_row_in_archive_order":{"model":"Prob-CBR","paper_title":"Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion","paper_url":"/paper/probabilistic-case-based-reasoning-for-open","paper_date":"2020-10-07","arxiv_id":"2010.03548","code_links":[{"title":"ameyagodbole/Prob-CBR","url":"https://github.com/ameyagodbole/Prob-CBR"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-tsp-hcp-benchmark-set","slug":"link-prediction-on-tsp-hcp-benchmark-set","dataset":"TSP/HCP Benchmark set","dataset_url":"/dataset/tsp-hcp-benchmark-set","rows_in_archive":4,"metrics":["F1"],"first_row_in_archive_order":{"model":"TGT-Agx4","paper_title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","paper_url":"/paper/triplet-interaction-improves-graph","paper_date":"2024-02-07","arxiv_id":"2402.04538","code_links":[{"title":"shamim-hussain/egt_pytorch","url":"https://github.com/shamim-hussain/egt_pytorch"},{"title":"shamim-hussain/tgt","url":"https://github.com/shamim-hussain/tgt"},{"title":"shamim-hussain/egt_triangular","url":"https://github.com/shamim-hussain/egt_triangular"}],"syntology":{"n":13,"n_ran":10,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-dblp","slug":"link-prediction-on-dblp","dataset":"DBLP","dataset_url":"/dataset/dblp","rows_in_archive":3,"metrics":["AUC","AP"],"first_row_in_archive_order":{"model":"GLACE","paper_title":"Gaussian Embedding of Large-scale Attributed Graphs","paper_url":"/paper/gaussian-embedding-of-large-scale-attributed","paper_date":"2019-12-02","arxiv_id":"1912.00536","code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-jf17k","slug":"link-prediction-on-jf17k","dataset":"JF17K","dataset_url":null,"rows_in_archive":3,"metrics":["MRR","Hit@1","Hit@10","Hit@5","H@1","H@10"],"first_row_in_archive_order":{"model":"HAHE","paper_title":"HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level","paper_url":"/paper/hahe-hierarchical-attention-for-hyper","paper_date":"2023-05-11","arxiv_id":"2305.06588","code_links":[{"title":"lhrlab/hahe","url":"https://github.com/lhrlab/hahe"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-kg20c","slug":"link-prediction-on-kg20c","dataset":"KG20C","dataset_url":"/dataset/kg20c","rows_in_archive":3,"metrics":["MRR","Hits@1","Hits@3","Hits@10"],"first_row_in_archive_order":{"model":"MEI (small)","paper_title":"Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion","paper_url":"/paper/multi-partition-embedding-interaction-with","paper_date":"2020-06-29","arxiv_id":"2006.16365","code_links":[{"title":"tranhungnghiep/AnalyzeKGE","url":"https://github.com/tranhungnghiep/AnalyzeKGE"},{"title":"tranhungnghiep/MEI-KGE","url":"https://github.com/tranhungnghiep/MEI-KGE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-citeseer-biased-evaluation","slug":"link-prediction-on-citeseer-biased-evaluation","dataset":"Citeseer (biased evaluation)","dataset_url":"/dataset/citeseer","rows_in_archive":2,"metrics":["AP","AUC","Accuracy"],"first_row_in_archive_order":{"model":"GraphStar (double weight on positive examples)","paper_title":"Graph Star Net for Generalized Multi-Task Learning","paper_url":"/paper/graph-star-net-for-generalized-multi-task-1","paper_date":"2019-06-21","arxiv_id":"1906.12330","code_links":[{"title":"graph-star-team/graph_star","url":"https://github.com/graph-star-team/graph_star"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-cora-biased-evaluation","slug":"link-prediction-on-cora-biased-evaluation","dataset":"Cora (biased evaluation)","dataset_url":"/dataset/cora","rows_in_archive":2,"metrics":["AP","AUC","Accuracy"],"first_row_in_archive_order":{"model":"GraphStar (double weight on positive examples)","paper_title":"Graph Star Net for Generalized Multi-Task Learning","paper_url":"/paper/graph-star-net-for-generalized-multi-task-1","paper_date":"2019-06-21","arxiv_id":"1906.12330","code_links":[{"title":"graph-star-team/graph_star","url":"https://github.com/graph-star-team/graph_star"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-decagon","slug":"link-prediction-on-decagon","dataset":"Decagon","dataset_url":"/dataset/decagon","rows_in_archive":2,"metrics":["AUROC","AUPRC","mAP@50"],"first_row_in_archive_order":{"model":"Decagon","paper_title":"Modeling polypharmacy side effects with graph convolutional networks","paper_url":"/paper/modeling-polypharmacy-side-effects-with-graph","paper_date":"2018-02-02","arxiv_id":"1802.00543","code_links":[{"title":"mims-harvard/decagon","url":"https://github.com/mims-harvard/decagon"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-douban","slug":"link-prediction-on-douban","dataset":"Douban","dataset_url":"/dataset/douban","rows_in_archive":2,"metrics":["AUC"],"first_row_in_archive_order":{"model":"HSRL (DW)","paper_title":"Learning Topological Representation for Networks via Hierarchical Sampling","paper_url":"/paper/learning-topological-representation-for","paper_date":"2019-02-15","arxiv_id":"1902.06684","code_links":[{"title":"fuguoji/HSRL","url":"https://github.com/fuguoji/HSRL"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-gps","slug":"link-prediction-on-gps","dataset":"GPS","dataset_url":null,"rows_in_archive":2,"metrics":["AUC","AUPR"],"first_row_in_archive_order":{"model":"Hyper-SAGNN-E","paper_title":"Hyper-SAGNN: a self-attention based graph neural network for hypergraphs","paper_url":"/paper/hyper-sagnn-a-self-attention-based-graph-1","paper_date":"2019-11-06","arxiv_id":"1911.02613","code_links":[{"title":"ma-compbio/Hyper-SAGNN","url":"https://github.com/ma-compbio/Hyper-SAGNN"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-livejournal","slug":"link-prediction-on-livejournal","dataset":"LiveJournal","dataset_url":null,"rows_in_archive":2,"metrics":["Hits@10","MR","MRR"],"first_row_in_archive_order":{"model":"PBG (1 partition)","paper_title":"PyTorch-BigGraph: A Large-scale Graph Embedding System","paper_url":"/paper/pytorch-biggraph-a-large-scale-graph","paper_date":"2019-03-28","arxiv_id":"1903.12287","code_links":[{"title":"facebookresearch/PyTorch-BigGraph","url":"https://github.com/facebookresearch/PyTorch-BigGraph"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-movielens-1m","slug":"link-prediction-on-movielens-1m","dataset":"MovieLens 1M","dataset_url":"/dataset/movielens","rows_in_archive":2,"metrics":["AUPR","AUC"],"first_row_in_archive_order":{"model":"Hyper-SAGNN-W","paper_title":"Hyper-SAGNN: a self-attention based graph neural network for hypergraphs","paper_url":"/paper/hyper-sagnn-a-self-attention-based-graph-1","paper_date":"2019-11-06","arxiv_id":"1911.02613","code_links":[{"title":"ma-compbio/Hyper-SAGNN","url":"https://github.com/ma-compbio/Hyper-SAGNN"}],"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-ppi","slug":"link-prediction-on-ppi","dataset":"PPI","dataset_url":"/dataset/ppi","rows_in_archive":2,"metrics":["AP","AUC","Accuracy"],"first_row_in_archive_order":{"model":"PPPNE","paper_title":"PPPNE: Personalized proximity preserved network embedding","paper_url":"/paper/pppne-personalized-proximity-preserved","paper_date":"2022-02-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-pubmed-biased-evaluation","slug":"link-prediction-on-pubmed-biased-evaluation","dataset":"Pubmed (biased evaluation)","dataset_url":"/dataset/pubmed","rows_in_archive":2,"metrics":["AP","AUC","Accuracy"],"first_row_in_archive_order":{"model":"GraphStar (double weight on positive examples)","paper_title":"Graph Star Net for Generalized Multi-Task Learning","paper_url":"/paper/graph-star-net-for-generalized-multi-task-1","paper_date":"2019-06-21","arxiv_id":"1906.12330","code_links":[{"title":"graph-star-team/graph_star","url":"https://github.com/graph-star-team/graph_star"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-usair","slug":"link-prediction-on-usair","dataset":"USAir","dataset_url":null,"rows_in_archive":2,"metrics":["AUC"],"first_row_in_archive_order":{"model":"SEAL","paper_title":"Link Prediction Based on Graph Neural Networks","paper_url":"/paper/link-prediction-based-on-graph-neural","paper_date":"2018-02-27","arxiv_id":"1802.09691","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/seal"},{"title":"muhanzhang/SEAL","url":"https://github.com/muhanzhang/SEAL"},{"title":"facebookresearch/SEAL_OGB","url":"https://github.com/facebookresearch/SEAL_OGB"},{"title":"venomouscyanide/s3grl","url":"https://github.com/venomouscyanide/s3grl"},{"title":"fs302/EasyLink","url":"https://github.com/fs302/EasyLink/blob/main/example/ogbl_ppa_ra.py"},{"title":"fs302/EasyLink","url":"https://github.com/fs302/EasyLink"},{"title":"venomouscyanide/s3grl_ogb","url":"https://github.com/venomouscyanide/s3grl_ogb"},{"title":"venomouscyanide/S3GRL_OGB","url":"https://github.com/venomouscyanide/S3GRL_OGB"},{"title":"arianemarandon/linkpredconf","url":"https://github.com/arianemarandon/linkpredconf"},{"title":"sreycodes/YLR","url":"https://github.com/sreycodes/YLR"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/link-prediction-on-wd50k","slug":"link-prediction-on-wd50k","dataset":"Temp8","dataset_url":null,"rows_in_archive":2,"metrics":["Hit@1","Hit@10","MRR"],"first_row_in_archive_order":{"model":"HAHE","paper_title":"HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level","paper_url":"/paper/hahe-hierarchical-attention-for-hyper","paper_date":"2023-05-11","arxiv_id":"2305.06588","code_links":[{"title":"lhrlab/hahe","url":"https://github.com/lhrlab/hahe"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-wiki","slug":"link-prediction-on-wiki","dataset":"Wiki","dataset_url":"/dataset/wiki","rows_in_archive":2,"metrics":["AUC"],"first_row_in_archive_order":{"model":null,"paper_title":"An Effective Graph Learning based Approach for Temporal Link Prediction: The First Place of WSDM Cup 2022","paper_url":"/paper/an-effective-graph-learning-based-approach","paper_date":"2022-03-01","arxiv_id":"2203.01820","code_links":[{"title":"im0qianqian/WSDM2022TGP-AntGraph","url":"https://github.com/im0qianqian/WSDM2022TGP-AntGraph"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-yago15k-1","slug":"link-prediction-on-yago15k-1","dataset":"YAGO15k","dataset_url":"/dataset/yago","rows_in_archive":2,"metrics":["MRR"],"first_row_in_archive_order":{"model":"TNTComplEx (x10)","paper_title":"Tensor Decompositions for temporal knowledge base completion","paper_url":"/paper/tensor-decompositions-for-temporal-knowledge-1","paper_date":"2020-04-10","arxiv_id":"2004.04926","code_links":[{"title":"apoorvumang/CronKGQA","url":"https://github.com/apoorvumang/CronKGQA"},{"title":"facebookresearch/tkbc","url":"https://github.com/facebookresearch/tkbc"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-yago37","slug":"link-prediction-on-yago37","dataset":"YAGO37","dataset_url":"/dataset/yago","rows_in_archive":2,"metrics":["Hits@1","Hits@10","Hits@3","Hits@5","MRR"],"first_row_in_archive_order":{"model":"SEEK","paper_title":"SEEK: Segmented Embedding of Knowledge Graphs","paper_url":"/paper/seek-segmented-embedding-of-knowledge-graphs","paper_date":"2020-05-02","arxiv_id":"2005.00856","code_links":[{"title":"Wentao-Xu/SEEK","url":"https://github.com/Wentao-Xu/SEEK"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-youtube","slug":"link-prediction-on-youtube","dataset":"YouTube","dataset_url":null,"rows_in_archive":2,"metrics":["F1-Score","Macro F1","Micro F1","PR AUC","ROC AUC"],"first_row_in_archive_order":{"model":"GATNE-T","paper_title":"Representation Learning for Attributed Multiplex Heterogeneous Network","paper_url":"/paper/190501669","paper_date":"2019-05-05","arxiv_id":"1905.01669","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T"},{"title":"THUDM/GATNE","url":"https://github.com/THUDM/GATNE"},{"title":"cenyk1230/GATNE","url":"https://github.com/cenyk1230/GATNE"},{"title":"SY1706203/GATNE","url":"https://github.com/SY1706203/GATNE"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-abstrct-neoplasm","slug":"link-prediction-on-abstrct-neoplasm","dataset":"AbstRCT - Neoplasm","dataset_url":"/dataset/abstrct-neoplasm","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"ResAttArg","paper_title":"Multi-Task Attentive Residual Networks for Argument Mining","paper_url":"/paper/multi-task-attentive-residual-networks-for","paper_date":"2021-02-24","arxiv_id":"2102.12227","code_links":[{"title":"AGalassi/StructurePrediction18","url":"https://github.com/AGalassi/StructurePrediction18"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-acm","slug":"link-prediction-on-acm","dataset":"ACM","dataset_url":"/dataset/acm","rows_in_archive":1,"metrics":["AP","AUC"],"first_row_in_archive_order":{"model":"GLACE","paper_title":"Gaussian Embedding of Large-scale Attributed Graphs","paper_url":"/paper/gaussian-embedding-of-large-scale-attributed","paper_date":"2019-12-02","arxiv_id":"1912.00536","code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-aksw-bib","slug":"link-prediction-on-aksw-bib","dataset":"AKSW-bib","dataset_url":null,"rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3"],"first_row_in_archive_order":{"model":"KG2Vec LSTM","paper_title":"Expeditious Generation of Knowledge Graph Embeddings","paper_url":"/paper/expeditious-generation-of-knowledge-graph","paper_date":"2018-03-21","arxiv_id":"1803.07828","code_links":[{"title":"AKSW/KG2Vec","url":"https://github.com/AKSW/KG2Vec"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-alibaba","slug":"link-prediction-on-alibaba","dataset":"Alibaba","dataset_url":null,"rows_in_archive":1,"metrics":["F1-Score","PR AUC","ROC AUC"],"first_row_in_archive_order":{"model":"GATNE-I","paper_title":"Representation Learning for Attributed Multiplex Heterogeneous Network","paper_url":"/paper/190501669","paper_date":"2019-05-05","arxiv_id":"1905.01669","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T"},{"title":"THUDM/GATNE","url":"https://github.com/THUDM/GATNE"},{"title":"cenyk1230/GATNE","url":"https://github.com/cenyk1230/GATNE"},{"title":"SY1706203/GATNE","url":"https://github.com/SY1706203/GATNE"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-alibaba-s","slug":"link-prediction-on-alibaba-s","dataset":"Alibaba-S","dataset_url":null,"rows_in_archive":1,"metrics":["F1-Score","PR AUC","ROC AUC"],"first_row_in_archive_order":{"model":"GATNE-T","paper_title":"Representation Learning for Attributed Multiplex Heterogeneous Network","paper_url":"/paper/190501669","paper_date":"2019-05-05","arxiv_id":"1905.01669","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T"},{"title":"THUDM/GATNE","url":"https://github.com/THUDM/GATNE"},{"title":"cenyk1230/GATNE","url":"https://github.com/cenyk1230/GATNE"},{"title":"SY1706203/GATNE","url":"https://github.com/SY1706203/GATNE"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-amazon","slug":"link-prediction-on-amazon","dataset":"Amazon","dataset_url":null,"rows_in_archive":1,"metrics":["F1-Score","PR AUC","ROC AUC"],"first_row_in_archive_order":{"model":"GATNE-T","paper_title":"Representation Learning for Attributed Multiplex Heterogeneous Network","paper_url":"/paper/190501669","paper_date":"2019-05-05","arxiv_id":"1905.01669","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T"},{"title":"THUDM/GATNE","url":"https://github.com/THUDM/GATNE"},{"title":"cenyk1230/GATNE","url":"https://github.com/cenyk1230/GATNE"},{"title":"SY1706203/GATNE","url":"https://github.com/SY1706203/GATNE"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-aristo-v4","slug":"link-prediction-on-aristo-v4","dataset":"Aristo-v4","dataset_url":"/dataset/aristo-v4","rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"ComplEx-N3-RP","paper_title":"Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations","paper_url":"/paper/relation-prediction-as-an-auxiliary-training","paper_date":"2021-10-06","arxiv_id":"2110.02834","code_links":[{"title":"facebookresearch/ssl-relation-prediction","url":"https://github.com/facebookresearch/ssl-relation-prediction"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-cdcp","slug":"link-prediction-on-cdcp","dataset":"CDCP","dataset_url":"/dataset/cdcp","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"ResAttArg","paper_title":"Multi-Task Attentive Residual Networks for Argument Mining","paper_url":"/paper/multi-task-attentive-residual-networks-for","paper_date":"2021-02-24","arxiv_id":"2102.12227","code_links":[{"title":"AGalassi/StructurePrediction18","url":"https://github.com/AGalassi/StructurePrediction18"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-cit-hepph","slug":"link-prediction-on-cit-hepph","dataset":"Cit-HepPH","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Asymmetric Transitivity Preservation","paper_title":"ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation","paper_url":"/paper/atp-directed-graph-embedding-with-asymmetric","paper_date":"2018-11-02","arxiv_id":"1811.00839","code_links":[{"title":"zhenv5/atp","url":"https://github.com/zhenv5/atp"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-citeseer-nonstandard","slug":"link-prediction-on-citeseer-nonstandard","dataset":"Citeseer (nonstandard variant)","dataset_url":"/dataset/citeseer","rows_in_archive":1,"metrics":["AP","AUC"],"first_row_in_archive_order":{"model":"GLACE","paper_title":"Gaussian Embedding of Large-scale Attributed Graphs","paper_url":"/paper/gaussian-embedding-of-large-scale-attributed","paper_date":"2019-12-02","arxiv_id":"1912.00536","code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-collab","slug":"link-prediction-on-collab","dataset":"COLLAB","dataset_url":"/dataset/collab","rows_in_archive":1,"metrics":["Hits"],"first_row_in_archive_order":{"model":"GatedGCN-PE","paper_title":"Benchmarking Graph Neural Networks","paper_url":"/paper/benchmarking-graph-neural-networks","paper_date":"2020-03-02","arxiv_id":"2003.00982","code_links":[{"title":"graphdeeplearning/benchmarking-gnns","url":"https://github.com/graphdeeplearning/benchmarking-gnns"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/ogbn-arxiv/unimp_appnp_vnode_smooth"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/nodeproppred/ogbn-proteins/unimp_cross_feat"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/master/examples/GaAN"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/master/ogb_examples/nodeproppred/ogbn-arxiv"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL/tree/main/ogb_examples/graphproppred/ogbg_molpcba"},{"title":"PaddlePaddle/PGL","url":"https://github.com/PaddlePaddle/PGL"},{"title":"shamim-hussain/egt","url":"https://github.com/shamim-hussain/egt"},{"title":"karl-zhao/benchmarking-gnns-pyg","url":"https://github.com/karl-zhao/benchmarking-gnns-pyg"},{"title":"guillaumejaume/tuto-dl-on-graphs","url":"https://github.com/guillaumejaume/tuto-dl-on-graphs"},{"title":"chenfengzhao/gnnhls","url":"https://github.com/chenfengzhao/gnnhls"},{"title":"yashkotadia/GatedGCN-PATTERN","url":"https://github.com/yashkotadia/GatedGCN-PATTERN"},{"title":"changminwu/expandergnn","url":"https://github.com/changminwu/expandergnn"},{"title":"liketheflower/jimmy_dgl","url":"https://github.com/liketheflower/jimmy_dgl"},{"title":"icml2024357/hombasis-gnn","url":"https://github.com/icml2024357/hombasis-gnn"}],"syntology":{"n":23,"n_ran":1,"n_unverified":22,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-cora-nonstandard-variant","slug":"link-prediction-on-cora-nonstandard-variant","dataset":"Cora (nonstandard variant)","dataset_url":"/dataset/cora","rows_in_archive":1,"metrics":["AP","AUC"],"first_row_in_archive_order":{"model":"GLACE","paper_title":"Gaussian Embedding of Large-scale Attributed Graphs","paper_url":"/paper/gaussian-embedding-of-large-scale-attributed","paper_date":"2019-12-02","arxiv_id":"1912.00536","code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-ddb14","slug":"link-prediction-on-ddb14","dataset":"DDB14","dataset_url":null,"rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"ConE","paper_title":"Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones","paper_url":"/paper/modeling-heterogeneous-hierarchies-with","paper_date":"2021-10-28","arxiv_id":"2110.14923","code_links":[{"title":"snap-stanford/ConE","url":"https://github.com/snap-stanford/ConE"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-dr-inventor","slug":"link-prediction-on-dr-inventor","dataset":"DRI Corpus","dataset_url":"/dataset/dr-inventor","rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"ResAttArg","paper_title":"Multi-Task Attentive Residual Networks for Argument Mining","paper_url":"/paper/multi-task-attentive-residual-networks-for","paper_date":"2021-02-24","arxiv_id":"2102.12227","code_links":[{"title":"AGalassi/StructurePrediction18","url":"https://github.com/AGalassi/StructurePrediction18"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-drug-drug-interactions","slug":"link-prediction-on-drug-drug-interactions","dataset":"Drug-Drug Interactions","dataset_url":null,"rows_in_archive":1,"metrics":["AUPRC"],"first_row_in_archive_order":{"model":"HOGCN","paper_title":"Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks","paper_url":"/paper/predicting-biomedical-interactions-with","paper_date":"2020-10-16","arxiv_id":"2010.08516","code_links":[{"title":"kckishan/HOGCN-LP","url":"https://github.com/kckishan/HOGCN-LP"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-drug-target-interactions","slug":"link-prediction-on-drug-target-interactions","dataset":"Drug-target interactions","dataset_url":null,"rows_in_archive":1,"metrics":["AUPRC"],"first_row_in_archive_order":{"model":"HOGCN","paper_title":"Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks","paper_url":"/paper/predicting-biomedical-interactions-with","paper_date":"2020-10-16","arxiv_id":"2010.08516","code_links":[{"title":"kckishan/HOGCN-LP","url":"https://github.com/kckishan/HOGCN-LP"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb-auto","slug":"link-prediction-on-fb-auto","dataset":"FB-AUTO","dataset_url":null,"rows_in_archive":1,"metrics":["Hits@10","MRR","Hits@1"],"first_row_in_archive_order":{"model":"BoxE","paper_title":"BoxE: A Box Embedding Model for Knowledge Base Completion","paper_url":"/paper/boxe-a-box-embedding-model-for-knowledge-base","paper_date":"2020-07-13","arxiv_id":"2007.06267","code_links":[{"title":"ralphabb/BoxE","url":"https://github.com/ralphabb/BoxE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb15k-237-ind","slug":"link-prediction-on-fb15k-237-ind","dataset":"FB15k-237-ind","dataset_url":null,"rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"kNN-KGE","paper_title":"Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings","paper_url":"/paper/reasoning-through-memorization-nearest","paper_date":"2022-01-14","arxiv_id":"2201.05575","code_links":[{"title":"zjunlp/knn-kg","url":"https://github.com/zjunlp/knn-kg"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-fb15k-filtered","slug":"link-prediction-on-fb15k-filtered","dataset":"FB15k (filtered)","dataset_url":"/dataset/fb15k","rows_in_archive":1,"metrics":["Hits@10","MR"],"first_row_in_archive_order":{"model":"ParTransH","paper_title":"Efficient Parallel Translating Embedding For Knowledge Graphs","paper_url":"/paper/efficient-parallel-translating-embedding-for","paper_date":"2017-03-30","arxiv_id":"1703.10316","code_links":[{"title":"zdh2292390/ParTrans-X","url":"https://github.com/zdh2292390/ParTrans-X"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-gene-disease-interactions","slug":"link-prediction-on-gene-disease-interactions","dataset":"Gene-disease interactions","dataset_url":null,"rows_in_archive":1,"metrics":["AUPRC"],"first_row_in_archive_order":{"model":"HOGCN","paper_title":"Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks","paper_url":"/paper/predicting-biomedical-interactions-with","paper_date":"2020-10-16","arxiv_id":"2010.08516","code_links":[{"title":"kckishan/HOGCN-LP","url":"https://github.com/kckishan/HOGCN-LP"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-gnutella","slug":"link-prediction-on-gnutella","dataset":"Gnutella","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Asymmetric Transitivity Preservation","paper_title":"ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation","paper_url":"/paper/atp-directed-graph-embedding-with-asymmetric","paper_date":"2018-11-02","arxiv_id":"1811.00839","code_links":[{"title":"zhenv5/atp","url":"https://github.com/zhenv5/atp"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-go21","slug":"link-prediction-on-go21","dataset":"GO21","dataset_url":"/dataset/go21","rows_in_archive":1,"metrics":["Hit@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"ConE","paper_title":"Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones","paper_url":"/paper/modeling-heterogeneous-hierarchies-with","paper_date":"2021-10-28","arxiv_id":"2110.14923","code_links":[{"title":"snap-stanford/ConE","url":"https://github.com/snap-stanford/ConE"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-imdb","slug":"link-prediction-on-imdb","dataset":"IMDb","dataset_url":"/dataset/imdb-movie-reviews","rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Event2vec","paper_title":"Representation Learning for Heterogeneous Information Networks via Embedding Events","paper_url":"/paper/representation-learning-for-heterogeneous","paper_date":"2019-01-29","arxiv_id":"1901.10234","code_links":[{"title":"fuguoji/Event2vec","url":"https://github.com/fuguoji/Event2vec"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-lastfm","slug":"link-prediction-on-lastfm","dataset":"Last.FM","dataset_url":null,"rows_in_archive":1,"metrics":["AP","AUC"],"first_row_in_archive_order":{"model":"MAGNN","paper_title":"MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding","paper_url":"/paper/magnn-metapath-aggregated-graph-neural","paper_date":"2020-02-05","arxiv_id":"2002.01680","code_links":[{"title":"cynricfu/MAGNN","url":"https://github.com/cynricfu/MAGNN"},{"title":"nmvdlei/PPMI_MAGNN","url":"https://github.com/nmvdlei/PPMI_MAGNN"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-mit","slug":"link-prediction-on-mit","dataset":"MIT","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"HSRL (DW)","paper_title":"Learning Topological Representation for Networks via Hierarchical Sampling","paper_url":"/paper/learning-topological-representation-for","paper_date":"2019-02-15","arxiv_id":"1902.06684","code_links":[{"title":"fuguoji/HSRL","url":"https://github.com/fuguoji/HSRL"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-ogbl-collab","slug":"link-prediction-on-ogbl-collab","dataset":"ogbl-collab","dataset_url":"/dataset/ogb","rows_in_archive":1,"metrics":["Test Hits@50"],"first_row_in_archive_order":{"model":"Edge2Node","paper_title":"Edge2Node: Reducing Edge Prediction to Node Classification","paper_url":"/paper/edge2node-reducing-edge-prediction-to-node","paper_date":"2023-11-06","arxiv_id":"2311.02921","code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-openbg500","slug":"link-prediction-on-openbg500","dataset":"OpenBG500","dataset_url":null,"rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"MoCoSA","paper_title":"MoCoSA: Momentum Contrast for Knowledge Graph Completion with Structure-Augmented Pre-trained Language Models","paper_url":"/paper/mocosa-momentum-contrast-for-knowledge-graph","paper_date":"2023-08-16","arxiv_id":"2308.08204","code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-protein-protein","slug":"link-prediction-on-protein-protein","dataset":"protein-protein interactions","dataset_url":null,"rows_in_archive":1,"metrics":["AUPRC"],"first_row_in_archive_order":{"model":"HOGCN","paper_title":"Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks","paper_url":"/paper/predicting-biomedical-interactions-with","paper_date":"2020-10-16","arxiv_id":"2010.08516","code_links":[{"title":"kckishan/HOGCN-LP","url":"https://github.com/kckishan/HOGCN-LP"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-pubmed-nonstandard-variant","slug":"link-prediction-on-pubmed-nonstandard-variant","dataset":"Pubmed (nonstandard variant)","dataset_url":"/dataset/pubmed","rows_in_archive":1,"metrics":["AP","AUC"],"first_row_in_archive_order":{"model":"GLACE","paper_title":"Gaussian Embedding of Large-scale Attributed Graphs","paper_url":"/paper/gaussian-embedding-of-large-scale-attributed","paper_date":"2019-12-02","arxiv_id":"1912.00536","code_links":[{"title":"bhagya-hettige/GLACE","url":"https://github.com/bhagya-hettige/GLACE"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-sins","slug":"link-prediction-on-sins","dataset":"SINS","dataset_url":"/dataset/sins","rows_in_archive":1,"metrics":["Scaled time-delay embeddings"],"first_row_in_archive_order":{"model":"mlp","paper_title":"Deep Learning in Mobile and Wireless Networking: A Survey","paper_url":"/paper/deep-learning-in-mobile-and-wireless","paper_date":"2018-03-12","arxiv_id":"1803.04311","code_links":[],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-twitter","slug":"link-prediction-on-twitter","dataset":"Twitter","dataset_url":null,"rows_in_archive":1,"metrics":["F1-Score","PR AUC","ROC AUC"],"first_row_in_archive_order":{"model":"GATNE-T","paper_title":"Representation Learning for Attributed Multiplex Heterogeneous Network","paper_url":"/paper/190501669","paper_date":"2019-05-05","arxiv_id":"1905.01669","code_links":[{"title":"dmlc/dgl","url":"https://github.com/dmlc/dgl/tree/master/examples/pytorch/GATNE-T"},{"title":"THUDM/GATNE","url":"https://github.com/THUDM/GATNE"},{"title":"cenyk1230/GATNE","url":"https://github.com/cenyk1230/GATNE"},{"title":"SY1706203/GATNE","url":"https://github.com/SY1706203/GATNE"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":1}}},{"leaderboard":"/sota/link-prediction-on-wiki-vote","slug":"link-prediction-on-wiki-vote","dataset":"Wiki-Vote","dataset_url":null,"rows_in_archive":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Asymmetric Transitivity Preservation","paper_title":"ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation","paper_url":"/paper/atp-directed-graph-embedding-with-asymmetric","paper_date":"2018-11-02","arxiv_id":"1811.00839","code_links":[{"title":"zhenv5/atp","url":"https://github.com/zhenv5/atp"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-wikidata12k","slug":"link-prediction-on-wikidata12k","dataset":"Wikidata12k","dataset_url":null,"rows_in_archive":1,"metrics":["MRR"],"first_row_in_archive_order":{"model":"TimePlex","paper_title":"Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols","paper_url":"/paper/temporal-knowledge-base-completion-new","paper_date":"2020-05-02","arxiv_id":"2005.05035","code_links":[{"title":"dair-iitd/tkbi","url":"https://github.com/dair-iitd/tkbi"}],"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":12}}},{"leaderboard":"/sota/link-prediction-on-wikipeople","slug":"link-prediction-on-wikipeople","dataset":"Wikipeople","dataset_url":null,"rows_in_archive":1,"metrics":["H@1","H@10","MRR"],"first_row_in_archive_order":{"model":"HAHE","paper_title":"HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level","paper_url":"/paper/hahe-hierarchical-attention-for-hyper","paper_date":"2023-05-11","arxiv_id":"2305.06588","code_links":[{"title":"lhrlab/hahe","url":"https://github.com/lhrlab/hahe"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/link-prediction-on-wn18-filtered","slug":"link-prediction-on-wn18-filtered","dataset":"WN18 (filtered)","dataset_url":"/dataset/wn18","rows_in_archive":1,"metrics":["Hits@10","MR"],"first_row_in_archive_order":{"model":"ParTransH","paper_title":"Efficient Parallel Translating Embedding For Knowledge Graphs","paper_url":"/paper/efficient-parallel-translating-embedding-for","paper_date":"2017-03-30","arxiv_id":"1703.10316","code_links":[{"title":"zdh2292390/ParTrans-X","url":"https://github.com/zdh2292390/ParTrans-X"}],"syntology":null}},{"leaderboard":"/sota/link-prediction-on-yago11k","slug":"link-prediction-on-yago11k","dataset":"Yago11k","dataset_url":"/dataset/yago","rows_in_archive":1,"metrics":["MRR"],"first_row_in_archive_order":{"model":"TimePlex","paper_title":"Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols","paper_url":"/paper/temporal-knowledge-base-completion-new","paper_date":"2020-05-02","arxiv_id":"2005.05035","code_links":[{"title":"dair-iitd/tkbi","url":"https://github.com/dair-iitd/tkbi"}],"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":12}}},{"leaderboard":"/sota/link-prediction-on-yago39k","slug":"link-prediction-on-yago39k","dataset":"YAGO39K","dataset_url":"/dataset/yago","rows_in_archive":1,"metrics":["Hits@1","Hits@10","Hits@3","MRR"],"first_row_in_archive_order":{"model":"TransC (bern)","paper_title":"Differentiating Concepts and Instances for Knowledge Graph Embedding","paper_url":"/paper/differentiating-concepts-and-instances-for","paper_date":"2018-11-12","arxiv_id":"1811.04588","code_links":[{"title":"davidlvxin/TransC","url":"https://github.com/davidlvxin/TransC"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/imdb-movie-reviews","name":"IMDb Movie Reviews","full_name":"","num_papers_in_archive":1787},{"url":"/dataset/movielens","name":"MovieLens","full_name":"MovieLens","num_papers_in_archive":1246},{"url":"/dataset/pubmed","name":"Pubmed","full_name":"","num_papers_in_archive":1236},{"url":"/dataset/ogb","name":"OGB","full_name":"Open Graph Benchmark","num_papers_in_archive":1000},{"url":"/dataset/fb15k","name":"FB15k","full_name":"Freebase 15K","num_papers_in_archive":641},{"url":"/dataset/cora","name":"Cora","full_name":"","num_papers_in_archive":602},{"url":"/dataset/wn18","name":"WN18","full_name":"WordNet18","num_papers_in_archive":485},{"url":"/dataset/fb15k-237","name":"FB15k-237","full_name":"","num_papers_in_archive":452},{"url":"/dataset/wn18rr","name":"WN18RR","full_name":"","num_papers_in_archive":394},{"url":"/dataset/citeseer","name":"Citeseer","full_name":"","num_papers_in_archive":381},{"url":"/dataset/yago","name":"YAGO","full_name":"Yet Another Great Ontology","num_papers_in_archive":359},{"url":"/dataset/ppi","name":"PPI","full_name":"Protein-Protein Interactions (PPI)","num_papers_in_archive":309},{"url":"/dataset/collab","name":"COLLAB","full_name":"","num_papers_in_archive":259},{"url":"/dataset/dblp","name":"DBLP","full_name":"Citation Network Dataset","num_papers_in_archive":218},{"url":"/dataset/nell","name":"NELL","full_name":"Never Ending Language Learning","num_papers_in_archive":177},{"url":"/dataset/snap","name":"SNAP","full_name":"Stanford Large Network Dataset Collection","num_papers_in_archive":174},{"url":"/dataset/nell-995","name":"NELL-995","full_name":"","num_papers_in_archive":127},{"url":"/dataset/yelp2018","name":"Yelp2018","full_name":"Yelp2018","num_papers_in_archive":125},{"url":"/dataset/icews","name":"ICEWS","full_name":"","num_papers_in_archive":113},{"url":"/dataset/wiki-cs","name":"Wiki-CS","full_name":"","num_papers_in_archive":111},{"url":"/dataset/yelp","name":"Yelp","full_name":"","num_papers_in_archive":86},{"url":"/dataset/orkut","name":"Orkut","full_name":"","num_papers_in_archive":85},{"url":"/dataset/douban","name":"Douban","full_name":"Douban Conversation Corpus","num_papers_in_archive":81},{"url":"/dataset/aminer","name":"AMiner","full_name":"","num_papers_in_archive":80},{"url":"/dataset/pascalvoc-sp","name":"Long Range Graph Benchmark (LRGB)","full_name":"","num_papers_in_archive":76},{"url":"/dataset/wikidata5m","name":"Wikidata5M","full_name":"","num_papers_in_archive":54},{"url":"/dataset/mmkg","name":"MMKG","full_name":"","num_papers_in_archive":49},{"url":"/dataset/string","name":"STRING","full_name":"STRING","num_papers_in_archive":35},{"url":"/dataset/biogrid","name":"BioGRID","full_name":"Biological General Repository for Interaction Datasets","num_papers_in_archive":34},{"url":"/dataset/ogb-lsc","name":"OGB-LSC","full_name":"OGB Large-Scale Challenge","num_papers_in_archive":34},{"url":"/dataset/decagon","name":"Decagon","full_name":"Bio-decagon","num_papers_in_archive":33},{"url":"/dataset/email-eu","name":"Email-EU","full_name":null,"num_papers_in_archive":33},{"url":"/dataset/yago3-10","name":"YAGO3-10","full_name":"Yet Another Great Ontology 3-10","num_papers_in_archive":20},{"url":"/dataset/umls","name":"UMLS","full_name":"Unified Medical Language System","num_papers_in_archive":19},{"url":"/dataset/cdcp","name":"CDCP","full_name":"Cornell eRulemaking Corpus","num_papers_in_archive":12},{"url":"/dataset/arxiv-astro-ph","name":"arXiv Astro-Ph","full_name":"","num_papers_in_archive":10},{"url":"/dataset/fb122","name":"FB122","full_name":"Freebase-122","num_papers_in_archive":10},{"url":"/dataset/proteinkg25","name":"ProteinKG25","full_name":"","num_papers_in_archive":8},{"url":"/dataset/wiki","name":"Wiki","full_name":"Web Traffic Time Series Forecasting","num_papers_in_archive":8},{"url":"/dataset/codex-medium","name":"CoDEx Medium","full_name":"","num_papers_in_archive":5},{"url":"/dataset/codex","name":"CoDEx Small","full_name":"","num_papers_in_archive":5},{"url":"/dataset/kg20c","name":"KG20C","full_name":"A scholarly knowledge graph benchmark dataset","num_papers_in_archive":5},{"url":"/dataset/tsp-hcp-benchmark-set","name":"TSP/HCP Benchmark set","full_name":"","num_papers_in_archive":5},{"url":"/dataset/acm","name":"ACM","full_name":"Association for Computing Machinery\nActive Contour Model\nalgebraic collective model\nand-Compare Module\nActive Contour Models","num_papers_in_archive":4},{"url":"/dataset/codex-large","name":"CoDEx Large","full_name":"","num_papers_in_archive":4},{"url":"/dataset/is-a","name":"IS-A","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/arxiv-gr-qc","name":"Arxiv GR-QC","full_name":"General Relativity and Quantum Cosmology collaboration network","num_papers_in_archive":3},{"url":"/dataset/fb15k-237-low","name":"FB15k-237-low","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/gdelt","name":"GDELT","full_name":"","num_papers_in_archive":3},{"url":"/dataset/dr-inventor","name":"DRI Corpus","full_name":"Dr. Inventor Multi-layer Scientific Corpus","num_papers_in_archive":2},{"url":"/dataset/dtgb","name":"DTGB","full_name":"Dynamic Text-attributed Graph Benchmark","num_papers_in_archive":2},{"url":"/dataset/herigraph","name":"HeriGraph","full_name":"Multimodal Machine Learning Datasets on Graphs of Heritage Values and Attributes","num_papers_in_archive":2},{"url":"/dataset/kinships","name":"Kinships","full_name":"","num_papers_in_archive":2},{"url":"/dataset/nations","name":"Nations","full_name":"","num_papers_in_archive":2},{"url":"/dataset/abstrct-neoplasm","name":"AbstRCT - Neoplasm","full_name":"","num_papers_in_archive":1},{"url":"/dataset/aristo-v4","name":"Aristo-v4","full_name":"Aristo Tuple KB Version 4","num_papers_in_archive":1},{"url":"/dataset/cve","name":"CVE","full_name":"Common Vulnerabilities and Exposures","num_papers_in_archive":1},{"url":"/dataset/fb1-5m","name":"FB1.5M","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/financial-dynamic-knowledge-graph","name":"Financial Dynamic Knowledge Graph","full_name":"","num_papers_in_archive":1},{"url":"/dataset/go21","name":"GO21","full_name":"","num_papers_in_archive":1},{"url":"/dataset/halvest-geometric","name":"HALvest-Geometric","full_name":"","num_papers_in_archive":1},{"url":"/dataset/htdm","name":"HTDM","full_name":"Hypertention Disease Medication","num_papers_in_archive":1},{"url":"/dataset/maple","name":"MAPLE","full_name":"","num_papers_in_archive":1},{"url":"/dataset/myket-android-application-install","name":"Myket Android Application Install","full_name":"","num_papers_in_archive":1},{"url":"/dataset/part-of","name":"PART-OF","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/pubmed-paper-reading-dataset","name":"PubMed Paper Reading Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sins","name":"SINS","full_name":"SINS","num_papers_in_archive":1}],"subtasks":[{"url":"/task/anchor-link-prediction","name":"Anchor link prediction"},{"url":"/task/calibration-for-link-prediction","name":"Calibration for Link Prediction"},{"url":"/task/dynamic-link-prediction","name":"Dynamic Link Prediction"},{"url":"/task/hyperedge-prediction","name":"Hyperedge Prediction"},{"url":"/task/inductive-link-prediction","name":"Inductive Link Prediction"},{"url":"/task/link-prediction-on-dh-kgs","name":"Link prediction on DH-KGs"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":974,"tagged_in_all":1949,"items":[{"url":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","repositories_listed":595,"syntology":{"n":946,"n_ran":600,"n_unverified":346,"n_pointer_only":451}},{"url":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","arxiv_id":"1710.10903","repositories_listed":93,"syntology":{"n":106,"n_ran":50,"n_unverified":56,"n_pointer_only":43}},{"url":"/paper/modeling-relational-data-with-graph","title":"Modeling Relational Data with Graph Convolutional Networks","date":"2017-03-17","arxiv_id":"1703.06103","repositories_listed":27,"syntology":{"n":32,"n_ran":10,"n_unverified":22,"n_pointer_only":15}},{"url":"/paper/variational-graph-auto-encoders","title":"Variational Graph Auto-Encoders","date":"2016-11-21","arxiv_id":"1611.07308","repositories_listed":22,"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/neural-graph-collaborative-filtering","title":"Neural Graph Collaborative Filtering","date":"2019-05-20","arxiv_id":"1905.08108","repositories_listed":21,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/inductive-representation-learning-on-large","title":"Inductive Representation Learning on Large Graphs","date":"2017-06-07","arxiv_id":"1706.02216","repositories_listed":20,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/node2vec-scalable-feature-learning-for","title":"node2vec: Scalable Feature Learning for Networks","date":"2016-07-03","arxiv_id":"1607.00653","repositories_listed":20,"syntology":{"n":25,"n_ran":8,"n_unverified":17,"n_pointer_only":3}},{"url":"/paper/graph-convolutional-matrix-completion","title":"Graph Convolutional Matrix Completion","date":"2017-06-07","arxiv_id":"1706.02263","repositories_listed":17,"syntology":null},{"url":"/paper/benchmarking-graph-neural-networks","title":"Benchmarking Graph Neural Networks","date":"2020-03-02","arxiv_id":"2003.00982","repositories_listed":15,"syntology":{"n":23,"n_ran":1,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/hierarchical-graph-representation-learning","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","date":"2018-06-22","arxiv_id":"1806.08804","repositories_listed":14,"syntology":{"n":20,"n_ran":1,"n_unverified":19,"n_pointer_only":0}},{"url":"/paper/gnn-explainer-a-tool-for-post-hoc-explanation","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","date":"2019-03-10","arxiv_id":"1903.03894","repositories_listed":12,"syntology":{"n":22,"n_ran":1,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/rotate-knowledge-graph-embedding-by","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","date":"2019-02-26","arxiv_id":"1902.10197","repositories_listed":10,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/evolvegcn-evolving-graph-convolutional","title":"EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs","date":"2019-02-26","arxiv_id":"1902.10191","repositories_listed":10,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/link-prediction-based-on-graph-neural","title":"Link Prediction Based on Graph Neural Networks","date":"2018-02-27","arxiv_id":"1802.09691","repositories_listed":10,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/embedding-entities-and-relations-for-learning","title":"Embedding Entities and Relations for Learning and Inference in Knowledge Bases","date":"2014-12-20","arxiv_id":"1412.6575","repositories_listed":10,"syntology":null},{"url":"/paper/learning-hierarchy-aware-knowledge-graph","title":"Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction","date":"2019-11-21","arxiv_id":"1911.09419","repositories_listed":9,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/hyperspherical-variational-auto-encoders","title":"Hyperspherical Variational Auto-Encoders","date":"2018-04-03","arxiv_id":"1804.00891","repositories_listed":9,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/complex-embeddings-for-simple-link-prediction","title":"Complex Embeddings for Simple Link Prediction","date":"2016-06-20","arxiv_id":"1606.06357","repositories_listed":9,"syntology":null},{"url":"/paper/line-large-scale-information-network","title":"LINE: Large-scale Information Network Embedding","date":"2015-03-12","arxiv_id":"1503.03578","repositories_listed":9,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/how-attentive-are-graph-attention-networks","title":"How Attentive are Graph Attention Networks?","date":"2021-05-30","arxiv_id":"2105.14491","repositories_listed":8,"syntology":{"n":16,"n_ran":6,"n_unverified":10,"n_pointer_only":1}},{"url":"/paper/190412575","title":"Knowledge Graph Convolutional Networks for Recommender Systems","date":"2019-03-18","arxiv_id":"1904.12575","repositories_listed":8,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/convolutional-2d-knowledge-graph-embeddings","title":"Convolutional 2D Knowledge Graph Embeddings","date":"2017-07-05","arxiv_id":"1707.01476","repositories_listed":8,"syntology":null},{"url":"/paper/translating-embeddings-for-modeling-multi","title":"Translating Embeddings for Modeling Multi-relational Data","date":"2013-12-01","arxiv_id":null,"repositories_listed":8,"syntology":null},{"url":"/paper/ogb-lsc-a-large-scale-challenge-for-machine","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","date":"2021-03-17","arxiv_id":"2103.09430","repositories_listed":6,"syntology":null},{"url":"/paper/cluster-gcn-an-efficient-algorithm-for","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","date":"2019-05-20","arxiv_id":"1905.07953","repositories_listed":6,"syntology":null},{"url":"/paper/nscaching-simple-and-efficient-negative","title":"NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding","date":"2018-12-16","arxiv_id":"1812.06410","repositories_listed":6,"syntology":null},{"url":"/paper/neural-factorization-machines-for-sparse","title":"Neural Factorization Machines for Sparse Predictive Analytics","date":"2017-08-16","arxiv_id":"1708.05027","repositories_listed":6,"syntology":null},{"url":"/paper/structural-deep-network-embedding","title":"Structural Deep Network Embedding","date":"2016-06-01","arxiv_id":null,"repositories_listed":6,"syntology":null},{"url":"/paper/effect-of-choosing-loss-function-when-using-t","title":"Effect of Choosing Loss Function when Using T-batching for Representation Learning on Dynamic Networks","date":"2023-08-13","arxiv_id":"2308.06862","repositories_listed":5,"syntology":null},{"url":"/paper/inductive-representation-learning-on-temporal-1","title":"Inductive Representation Learning on Temporal Graphs","date":"2020-02-19","arxiv_id":"2002.07962","repositories_listed":5,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}}],"syntology_records":19,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}