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

2025-05-27

AI Summary

In knowledge graph embedding, relation-specific entity transformations improve performance but often yield semantically inconsistent embeddings before and after transformation: (i) relation representations lack coherence, causing ambiguous transformations for similar relations; and (ii) existing semantic filtering approaches (e.g., SFBR) over-rely on entity regularization, blurring score distributions across relations. To address these issues, we propose the Relation-Semantic Consistency Filter (RSCF), the first framework integrating three novel mechanisms—shared affine transformation, root-based entity transformation, and change-magnitude normalization—alongside dedicated relation transformation and prediction modules to enforce semantic preservation. RSCF operates as a plug-in compatible with both distance-based and tensor factorization models, incorporating relation-semantic constraints and joint entity-relation regularization. Experiments demonstrate that RSCF significantly outperforms state-of-the-art methods on knowledge graph completion, exhibits strong robustness across high- and low-frequency relations, and effectively mitigates score distribution confusion.

Technology Category

• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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), containing more consistent entity-transformation characterized by three features: 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.

Problem

• Ensures consistency in entity-transformation embeddings for similar relations
• Addresses loss of inductive bias due to inconsistent embedding differences
• Improves relation-specific semantics via shared affine transformation and normalization

Innovation

• Shared affine transformation for relation embeddings
• Rooted entity-transformation with added embedding
• Normalization to prevent scale reduction