Enhancing inductive knowledge graph completion with contextual relation topology learning

doi:10.1016/j.knosys.2025.114302

Return

Enhancing inductive knowledge graph completion with contextual relation topology learning

2025-08-24

PRE

DOI：10.1016/j.knosys.2025.114302

Original

Original request for help

Save

Abstract

En 中文

Knowledge graph completion (KGC) plays a crucial role in inferring missing triples within knowledge graphs (KGs), while inductive KGC extends this by enabling predictions for previously unseen entities, allowing dynamic updates in KGs. Recent methods define entity-independent features and utilize Graph Neural Networks (GNNs) to extract them from subgraphs surrounding the target triplet, which are then used to represent relational semantics and logical rules for reasoning. However, the inductive capabilities of existing work is limited as they consider limited entity-independent features. To address this issue, we introduce a novel Contextual Relation Topology Learning-based GNN framework for inductive KGC, namely CRTL, which considers a broader range of entity-independent features. We observe that subgraph structural features, relation correlation patterns, and entity-relation interactions are crucial entity-independent features for inductive KGC. Moreover, relation correlation patterns and entity-relation interactions are complementary. Specifically, we construct enclosing subgraphs to extract subgraph structural features, relational graphs to model the correlations between relations, and context subgraphs to capture the interactions between entities and relations. In addition, we design a scoring function that dynamically adjusts the contributions of these features. Our extensive experiments on benchmark datasets reveal that CRTL surpasses current state-of-the-art methods, demonstrating improvements of 9.68 % on WN18RR v1 and 12.86 % on FB15K-237 v1 when compared to the suboptimal results.