mlsanityData to 7 Oct 2026

How to Turn Your Knowledge Graph Embeddings into Generative Models

arXiv 2305.15944 ↗First posted 25 May 2023cs.LG cs.AIcited by 20

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 33 of its 78 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

33 of 78 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2018Demystifying MMD GANscited by 1,268
  5. 2016Complex Embeddings for Simple Link Predictioncited by 897
  6. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  7. 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
  8. 2020Knowledge Graphscited by 619
  9. 2019TuckER: Tensor Factorization for Knowledge Graph Completioncited by 290
  10. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 264
  11. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  12. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
21 more
  1. 2020Complex Query Answering with Neural Link Predictorscited by 98
  2. 2013A Semantic Matching Energy Function for Learning with Multi-relational Datacited by 61
  3. 2016On the Latent Variable Interpretation in Sum-Product Networkscited by 40
  4. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  5. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  6. 2015Type-Constrained Representation Learning in Knowledge Graphscited by 34
  7. 2021Tensor-Train Density Estimationcited by 30
  8. 2015TransG : A Generative Mixture Model for Knowledge Graph Embeddingcited by 28
  9. 2020Strudel: Learning Structured-Decomposable Probabilistic Circuitscited by 24
  10. 2014Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inferencecited by 23
  11. 2021Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoningcited by 22
  12. 2019Probability Calibration for Knowledge Graph Embedding Modelscited by 20
  13. 2016Visualizing and Understanding Sum-Product Networkscited by 18
  14. 2021Understanding the Performance of Knowledge Graph Embeddings in Drug Discoverycited by 18
  15. 2017Adversarial Sets for Regularising Neural Link Predictorscited by 15
  16. 2020Knowledge Base Completion: Baseline strikes back (Again)cited by 12
  17. 2015Learning with Memory Embeddingscited by 8
  18. 2021The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decodingcited by 8
  19. 2020Symbolic Querying of Vector Spaces: Probabilistic Databases Meets Relational Embeddingscited by 6
  20. 2017Fast Linear Model for Knowledge Graph Embeddingscited by 4
  21. 2021A Probabilistic Framework for Knowledge Graph Data Augmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 7; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023Subtractive Mixture Models via Squaring: Representation and Learningcited by 39
  2. 2024Scaling Tractable Probabilistic Circuits: A Systems Perspectivecited by 23
  3. 2023Image Inpainting via Tractable Steering of Diffusion Modelscited by 22
  4. 2024What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?cited by 22
  5. 2024Sum of Squares Circuitscited by 21
  6. 2023Knowledge Graph Embeddings in the Biomedical Domain: Are They Useful? A Look at Link Prediction, Rule Learning, and Downstream Polypharmacy Taskscited by 9
  7. 2024Scaling Continuous Latent Variable Models as Probabilistic Integral Circuitscited by 9
  8. 2024Is Complex Query Answering Really Complex?cited by 7
  9. 2025How to Square Tensor Networks and Circuits Without Squaring Themcited by 5
  10. 2025Tractable Representation Learning with Probabilistic Circuitscited by 4
  11. 2024Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Modelcited by 3
  12. 2024On Faster Marginalization with Squared Circuits via Orthonormalizationcited by 2
8 more
  1. 2025DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusioncited by 2
  2. 2023Temporal Smoothness Regularisers for Neural Link Predictorscited by 1
  3. 2025Probabilistic Graph Circuits: Deep Generative Models for Tractable Probabilistic Inference over Graphscited by 1
  4. 2025Squared families: Searching beyond regular probability modelscited by 1
  5. 2025On the Theoretical Limitations of Embedding-based Link Predictioncited by 1
  6. 2026How to Approximate Inference with Subtractive Mixture Modelscited by 1
  7. 2025Unifying Post-hoc Explanations of Knowledge Graph Completionscited by 0
  8. 2026Autoregressive Models for Knowledge Graph Generationcited by 0