TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction

TL;DR

TranSHER introduces a relation-specific translation mechanism to improve knowledge graph embedding, overcoming hyper-ellipsoid restrictions and enhancing link prediction performance across diverse datasets.

Contribution

The paper proposes TranSHER, a novel score function that relaxes entity distribution constraints in knowledge graph embedding by using relation-specific translations.

Findings

Significant improvements in link prediction accuracy.

Effective generalization across different datasets.

Enhanced modeling of complex relations.

Abstract

Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task. One existing efficient method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion. To address this issue, we propose a novel score function TranSHER, which leverages relation-specific translations between head and tail entities to relax the constraint of hyper-ellipsoid restrictions. By introducing an intuitive and simple relation-specific translation, TranSHER can provide more direct guidance on optimization and capture more semantic characteristics of entities with complex relations. Experimental results show that TranSHER achieves significant performance improvements on link prediction and generalizes well to datasets in different domains and scales. Our codes are public available at https://github.com/yizhilll/TranSHER.