Papers › Translating Embeddings for Modeling Multi-relational Data

Translating Embeddings for Modeling Multi-relational Data

1 Dec 2013NeurIPS 2013 12archive 2025-07-28

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko

We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose, TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assumption proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.

PaperPDFCode

Code

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 Prediction

Datasets

Introduced by this paper, per the archive.

FB15kWN18WN18RR

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB122 TransE HITS@3 58.9 #5 of 5 Archive leaderboard report
Link Prediction FB122 TransE Hits@10 70.2 #5 of 5 Archive leaderboard report
Link Prediction FB122 TransE Hits@5 64.2 #5 of 5 Archive leaderboard report
Link Prediction FB122 TransE MRR 48.0 #5 of 5 Archive leaderboard report
Link Prediction FB15k TransE Hits@10 0.471 #23 of 23 Archive leaderboard report
Link Prediction FB15k TransE MR 125 #23 of 23 Archive leaderboard report
Link Prediction FB15k-237 TransE Hits@1 0.1987 #51 of 75 Archive leaderboard report
Link Prediction FB15k-237 TransE Hits@10 .4709 #51 of 75 Archive leaderboard report
Link Prediction FB15k-237 TransE MRR 0.2904 #51 of 75 Archive leaderboard report
Link Prediction UMLS TransE Hits@10 0.989 #8 of 10 Archive leaderboard report
Link Prediction UMLS TransE MR 1.84 #8 of 10 Archive leaderboard report
Link Prediction WN18 TransE Hits@10 0.754 #32 of 37 Archive leaderboard report
Link Prediction WN18 TransE MR 263 #32 of 37 Archive leaderboard report
Link Prediction WN18RR TransE Hits@1 0.4226 #48 of 75 Archive leaderboard report
Link Prediction WN18RR TransE Hits@10 0.5555 #48 of 75 Archive leaderboard report
Link Prediction WN18RR TransE MRR 0.4659 #48 of 75 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.

Methods

Introduced by this paper: TransE

TransE

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