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 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

ttrouill/complex officialmentioned in paperNOASSERTIONSyntology: not harvested report
bi-graph/emgraph mentioned on GitHubtfSyntology: not harvested report
dayanayuan/raa-kgc mentioned on GitHubpytorchSyntology: not harvested report
iesl/geometric_graph_embedding mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Local Identifiability in Probabilistic Box Embeddings (arXiv:2010.04831; that paper's own run record: 5 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; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
pykeen/pykeen mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs (arXiv:2203.07544; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
sntcristian/and-kge mentioned on GitHubpytorchSyntology: not harvested 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
stellargraph/stellargraph tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adversarial Examples on Graph Data: Deep Insights into Attack and Defense (arXiv:1903.01610; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 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 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