RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph

TL;DR

This paper introduces RSCF, a novel relation-semantics consistent filter for knowledge graph embeddings, improving semantic consistency and significantly enhancing performance in knowledge graph completion tasks.

Contribution

RSCF employs shared affine transformations, rooted entity transformations, and normalization to maintain semantic consistency in entity embeddings, addressing limitations of previous methods.

Findings

RSCF outperforms state-of-the-art KGE methods in knowledge graph completion.

RSCF demonstrates robustness across all relations and frequencies.

Semantic consistency preservation improves embedding quality.

Abstract

In knowledge graph embedding, leveraging relation specific entity transformation has markedly enhanced performance. However, the consistency of embedding differences before and after transformation remains unaddressed, risking the loss of valuable inductive bias inherent in the embeddings. This inconsistency stems from two problems. First, transformation representations are specified for relations in a disconnected manner, allowing dissimilar transformations and corresponding entity embeddings for similar relations. Second, a generalized plug-in approach as a SFBR (Semantic Filter Based on Relations) disrupts this consistency through excessive concentration of entity embeddings under entity-based regularization, generating indistinguishable score distributions among relations. In this paper, we introduce a plug-in KGE method, Relation-Semantics Consistent Filter (RSCF). Its entity transformation has three features for enhancing semantic consistency: 1) shared affine transformation of relation embeddings across all relations, 2) rooted entity transformation that adds an entity embedding to its change represented by the transformed vector, and 3) normalization of the change to prevent scale reduction. To amplify the advantages of consistency that preserve semantics on embeddings, RSCF adds relation transformation and prediction modules for enhancing the semantics. In knowledge graph completion tasks with distance-based and tensor decomposition models, RSCF significantly outperforms state-of-the-art KGE methods, showing robustness across all relations and their frequencies.