Papers › Complex Embeddings for Simple Link Prediction

Complex Embeddings for Simple Link Prediction

20 Jun 2016arXiv:1606.06357archive 2025-07-28

Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard

In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to solve this problem through latent factorization. However, here we make use of complex valued embeddings. The composition of complex embeddings can handle a large variety of binary relations, among them symmetric and antisymmetric relations. Compared to state-of-the-art models such as Neural Tensor Network and Holographic Embeddings, our approach based on complex embeddings is arguably simpler, as it only uses the Hermitian dot product, the complex counterpart of the standard dot product between real vectors. Our approach is scalable to large datasets as it remains linear in both space and time, while consistently outperforming alternative approaches on standard link prediction benchmarks.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ttrouill/complex officialmentioned in paperNOASSERTION report
bi-graph/emgraph mentioned on GitHubtf report
dayanayuan/raa-kgc mentioned on GitHubpytorch report
iesl/geometric_graph_embedding mentioned on GitHubpytorchApache-2.0 report
pykeen/pykeen mentioned on GitHubpytorchMIT report
sntcristian/and-kge mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Link PredictionPredictionRelational Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB122 ComplEx HITS@3 67.3 #4 of 5 Archive leaderboard report
Link Prediction FB122 ComplEx Hits@10 71.9 #4 of 5 Archive leaderboard report
Link Prediction FB122 ComplEx Hits@5 69.5 #4 of 5 Archive leaderboard report
Link Prediction FB122 ComplEx MRR 64.1 #4 of 5 Archive leaderboard report
Link Prediction FB15k-237 ComplEx Hits@10 0.428 #70 of 75 Archive leaderboard report
Link Prediction UMLS ComplEx Hits@10 0.967 #9 of 10 Archive leaderboard report
Link Prediction UMLS ComplEx MR 2.59 #9 of 10 Archive leaderboard report
Link Prediction WN18 ComplEx Hits@1 0.936 #26 of 37 Archive leaderboard report
Link Prediction WN18 ComplEx Hits@10 0.947 #26 of 37 Archive leaderboard report
Link Prediction WN18 ComplEx Hits@3 0.936 #26 of 37 Archive leaderboard report
Link Prediction WN18 ComplEx MRR 0.941 #26 of 37 Archive leaderboard report
Link Prediction WN18RR ComplEx Hits@1 0.410 #66 of 75 Archive leaderboard report
Link Prediction WN18RR ComplEx Hits@10 0.510 #66 of 75 Archive leaderboard report
Link Prediction WN18RR ComplEx MRR 0.440 #66 of 75 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx Ext. data No #13 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx Number of params 187648000 #13 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx Test MRR 0.8095 ± 0.0007 #13 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx Validation MRR 0.8105 ± 0.0001 #13 of 16 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (250dim) Ext. data No #25 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (250dim) Number of params 1250569500 #25 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (250dim) Test MRR 0.4027 ± 0.0027 #25 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (250dim) Validation MRR 0.3759 ± 0.0016 #25 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (50dim) Ext. data No #26 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (50dim) Number of params 250113900 #26 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (50dim) Test MRR 0.3804 ± 0.0022 #26 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 ComplEx (50dim) Validation MRR 0.3534 ± 0.0052 #26 of 30 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections