mlsanityData to 14 Oct 2026

Prior Bilinear Based Models for Knowledge Graph Completion

arXiv 2309.13834 ↗First posted 25 Sep 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Bilinear based models are powerful and widely used approaches for Knowledge Graphs Completion (KGC). Although bilinear based models have achieved significant advances, these studies mainly concentrate on posterior properties (based on evidence, e.g. symmetry pattern) while neglecting the prior properties. In this paper, we find a prior property named "the law of identity" that cannot be captured by bilinear based models, which hinders them from comprehensively modeling the characteristics of KGs. To address this issue, we introduce a solution called Unit Ball Bilinear Model (UniBi). This model not only achieves theoretical superiority but also offers enhanced interpretability and performance by minimizing ineffective learning through minimal constraints. Experiments demonstrate that UniBi models the prior property and verify its interpretability and performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 43 references that are in the map. First posted on arXiv 25 Sep 2023.

Builds on

27 of 43 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  5. 2016Complex Embeddings for Simple Link Predictioncited by 902
  6. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  7. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  8. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  9. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  10. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  11. 2020Low-Dimensional Hyperbolic Knowledge Graph Embeddingscited by 195
  12. 2015Holographic Embeddings of Knowledge Graphscited by 181
15 more
  1. 2019Quaternion Knowledge Graph Embeddingscited by 175
  2. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  3. 2017A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Networkcited by 143
  4. 2019Multi-relational Poincar'e Graph Embeddingscited by 126
  5. 2017Analogical Inference for Multi-Relational Embeddingscited by 69
  6. 2020PairRE: Knowledge Graph Embeddings via Paired Relation Vectorscited by 67
  7. 2017Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddingscited by 59
  8. 2019Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embeddingcited by 38
  9. 2020Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Studycited by 37
  10. 2020Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completioncited by 28
  11. 2019Relation Embedding with Dihedral Group in Knowledge Graphcited by 25
  12. 2016Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embeddingcited by 22
  13. 2017Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networkscited by 12
  14. 2021QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completioncited by 10
  15. 2020Knowledge Graph Embeddings in Geometric Algebrascited by 8

Built on by

Not cited yet.