Papers › How to Turn Your Knowledge Graph Embeddings into Generative Models

How to Turn Your Knowledge Graph Embeddings into Generative Models

25 May 2023NeurIPS 2023 11arXiv:2305.15944archive 2025-07-28

Lorenzo Loconte, Nicola Di Mauro, Robert Peharz, Antonio Vergari

Some of the most successful knowledge graph embedding (KGE) models for link prediction -- CP, RESCAL, TuckER, ComplEx -- can be interpreted as energy-based models. Under this perspective they are not amenable for exact maximum-likelihood estimation (MLE), sampling and struggle to integrate logical constraints. This work re-interprets the score functions of these KGEs as circuits -- constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs. Our interpretation comes with little or no loss of performance for link prediction, while the circuits framework unlocks exact learning by MLE, efficient sampling of new triples, and guarantee that logical constraints are satisfied by design. Furthermore, our models scale more gracefully than the original KGEs on graphs with millions of entities.

PaperPDFConference PDFCode

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

Code

april-tools/gekcs officialmentioned in paperpytorch 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

Graph EmbeddingKnowledge Graph EmbeddingKnowledge Graph EmbeddingsLink Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-biokg ComplEx^2 Ext. data No #4 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx^2 Number of params 187648000 #4 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx^2 Test MRR 0.8583 ± 0.0005 #4 of 16 Archive leaderboard report
Link Property Prediction ogbl-biokg ComplEx^2 Validation MRR 0.8592 ± 0.0004 #4 of 16 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

RESCALTuckER

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