Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion

TL;DR

This paper introduces CPSR, a novel framework for inductive knowledge graph completion that effectively captures structural and semantic information, improving reasoning over emerging entities and achieving state-of-the-art results.

Contribution

The paper proposes CPSR, a new method combining query-dependent masking and semantic scoring to enhance inductive KGC, addressing noise and long-range dependency challenges.

Findings

CPSR outperforms existing methods on benchmark datasets.

The query-dependent masking reduces noise in reasoning paths.

Semantic scoring improves the accuracy of link prediction.

Abstract

Conventional Knowledge Graph Completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to perform effectively in scenarios involving emerging entities. Inductive KGC methods can handle the emerging entities and relations in KGs, offering greater dynamic adaptability. While existing inductive KGC methods have achieved some success, they also face challenges, such as susceptibility to noisy structural information during reasoning and difficulty in capturing long-range dependencies in reasoning paths. To address these challenges, this paper proposes the Cumulative Path-Level Semantic Reasoning for inductive knowledge graph completion (CPSR) framework, which simultaneously captures both the structural and semantic information of KGs to enhance the inductive KGC task. Specifically, the proposed CPSR employs a query-dependent masking module to adaptively mask noisy structural information while retaining important information closely related to the targets. Additionally, CPSR introduces a global semantic scoring module that evaluates both the individual contributions and the collective impact of nodes along the reasoning path within KGs. The experimental results demonstrate that CPSR achieves state-of-the-art performance.