Papers › Embedding Entities and Relations for Learning and Inference in Knowledge Bases

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

20 Dec 2014arXiv:1412.6575archive 2025-07-28

Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, Li Deng

We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functions. Under this framework, we compare a variety of embedding models on the link prediction task. We show that a simple bilinear formulation achieves new state-of-the-art results for the task (achieving a top-10 accuracy of 73.2% vs. 54.7% by TransE on Freebase). Furthermore, we introduce a novel approach that utilizes the learned relation embeddings to mine logical rules such as "BornInCity(a,b) and CityInCountry(b,c) => Nationality(a,c)". We find that embeddings learned from the bilinear objective are particularly good at capturing relational semantics and that the composition of relations is characterized by matrix multiplication. More interestingly, we demonstrate that our embedding-based rule extraction approach successfully outperforms a state-of-the-art confidence-based rule mining approach in mining Horn rules that involve compositional reasoning.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Sujit-O/pykg2vec mentioned on GitHubtfMITSyntology: not harvested report
awslabs/dgl-ke mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DGL-KE: Training Knowledge Graph Embeddings at Scale (arXiv:2004.08532; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
bi-graph/emgraph mentioned on GitHubtfSyntology: not harvested report
facebookresearch/PyTorch-BigGraph mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
giuseppefutia/semi mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Modeling Relational Data with Graph Convolutional Networks (arXiv:1703.06103; that paper's own run record: 18 ran (of which 3 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
sntcristian/and-kge mentioned on GitHubpytorchSyntology: not harvested report
thiviyant/intelligraphs mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
thu-keg/eakit mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (arXiv:1911.09419; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Accenture/AmpliGraph tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Embeddings from Knowledge Graphs With Numeric Edge Attributes (arXiv:2105.08683; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
pyg-team/pytorch_geometric pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning the Geometry of Data: A Mathematical Review of Shape Space Analysis (arXiv:2606.17022; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Link Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Prediction FB15k-237 DistMult Hits@10 0.419 #73 of 75 Archive leaderboard report
Link Prediction FB15k-237 DistMult MRR 0.241 #73 of 75 Archive leaderboard report
Link Prediction UMLS DistMult Hits@10 0.846 #10 of 10 Archive leaderboard report
Link Prediction UMLS DistMult MR 5.52 #10 of 10 Archive leaderboard report
Link Prediction WN18 DistMult Hits@1 0.728 #29 of 37 Archive leaderboard report
Link Prediction WN18 DistMult Hits@10 0.936 #29 of 37 Archive leaderboard report
Link Prediction WN18 DistMult Hits@3 0.914 #29 of 37 Archive leaderboard report
Link Prediction WN18 DistMult MR 902 #29 of 37 Archive leaderboard report
Link Prediction WN18 DistMult MRR 0.822 #29 of 37 Archive leaderboard report
Link Prediction WN18RR DisMult Hits@1 0.39 #74 of 75 Archive leaderboard report
Link Prediction WN18RR DisMult MRR 0.43 #74 of 75 Archive leaderboard report
Link Property Prediction ogbl-biokg DistMult Ext. data No #14 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg DistMult Number of params 187648000 #14 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg DistMult Test MRR 0.8043 ± 0.0003 #14 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg DistMult Validation MRR 0.8055 ± 0.0003 #14 of 16 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (500dim) Ext. data No #27 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (500dim) Number of params 1250569500 #27 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (500dim) Test MRR 0.3729 ± 0.0045 #27 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (500dim) Validation MRR 0.3506 ± 0.0042 #27 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (100dim) Ext. data No #28 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (100dim) Number of params 250113900 #28 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (100dim) Test MRR 0.3447 ± 0.0082 #28 of 30 Archive leaderboard report
Link Property Prediction ogbl-wikikg2 DistMult (100dim) Validation MRR 0.3150 ± 0.0088 #28 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.

Methods

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