Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing

TL;DR

This paper introduces a semantic-aware message passing method for knowledge graph completion that selectively focuses on relevant neighboring edges, improving prediction accuracy by reducing noise and over-smoothing.

Contribution

The proposed approach employs a semantic relevance evaluation and Top-K neighbor selection with multi-head attention to enhance knowledge graph completion.

Findings

Achieves superior performance on multiple benchmarks.

Effectively reduces noise and over-smoothing in message passing.

Improves link prediction accuracy by focusing on relevant context.

Abstract

Semantic context surrounding a triplet $(h, r, t)$ is crucial for Knowledge Graph Completion (KGC), providing vital cues for prediction. However, traditional node-based message passing mechanisms, when applied to knowledge graphs, often introduce noise and suffer from information dilution or over-smoothing by indiscriminately aggregating information from all neighboring edges. To address this challenge, we propose a semantic-aware relational message passing. A core innovation of this framework is the introduction of a semantic-aware Top-K neighbor selection strategy. Specifically, this strategy first evaluates the semantic relevance between a central node and its incident edges within a shared latent space, selecting only the Top-K most pertinent ones. Subsequently, information from these selected edges is effectively fused with the central node's own representation using a multi-head attention aggregator to generate a semantically focused node message. In this manner, our model not only leverages the structure and features of edges within the knowledge graph but also more accurately captures and propagates the contextual information most relevant to the specific link prediction task, thereby effectively mitigating interference from irrelevant information. Extensive experiments demonstrate that our method achieves superior performance compared to existing approaches on several established benchmarks.