Papers › Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding

Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding

11 Jan 2024arXiv:2401.05967archive 2025-07-28

Yihua Zhu, Hidetoshi Shimodaira

The primary aim of Knowledge Graph embeddings (KGE) is to learn low-dimensional representations of entities and relations for predicting missing facts. While rotation-based methods like RotatE and QuatE perform well in KGE, they face two challenges: limited model flexibility requiring proportional increases in relation size with entity dimension, and difficulties in generalizing the model for higher-dimensional rotations. To address these issues, we introduce OrthogonalE, a novel KGE model employing matrices for entities and block-diagonal orthogonal matrices with Riemannian optimization for relations. This approach enhances the generality and flexibility of KGE models. The experimental results indicate that our new KGE model, OrthogonalE, is both general and flexible, significantly outperforming state-of-the-art KGE models while substantially reducing the number of relation parameters.

PaperPDFCode

Code

yihuazhu111/orthogonale officialmentioned in papermentioned on GitHubpytorch 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 EmbeddingsRiemannian optimization

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

RotatESelf-Adversarial Negative Sampling

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