Relation prediction based on the attention-enhanced fusion of graph strcuture and multi-hop neighborhood information in knowledge graphs

• Published in: Data mining and knowledge discovery Vol. 39; no. 5; p. 56
• Main Authors: Liu, Yisi, Tao, Sha
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2025; Springer Nature B.V
• Subjects: Artificial Intelligence; Chemistry and Earth Sciences; Civil war; Computer Science; Data Mining and Knowledge Discovery; Graph theory; Graphical representations; Graphs; Information Storage and Retrieval; Knowledge representation; Learning; Message passing; Neighborhoods; Physics; Prediction models; Semantics; Statistics for Engineering; Attention mechanism; Multi-hop graph neural network; Relation prediction; Knowledge graph
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-025-01141-3

Relation prediction is a critical approach to addressing the incompleteness of knowledge graphs. Research has shown that learning long-term semantic dependency information from multi-hop neighbourhoods is essential for fully capturing the contextual semantics of knowledge graphs. Based on the complex graph structure of knowledge graphs, multi-hop neighbourhood structures include relational paths between entities and the multi-level local neighbourhoods of given entities. However, existing studies often focus on single-dimensional learning, making it prone to overlook specific patterns when predicting missing relations. Prior research relies on static path aggregation or sequence encoding methods, particularly in learning the multi-hop structures of relational paths, neglecting the dynamic interactions between relational paths.In this paper, we propose a model named R-APSC , which aims to learn contextual representations of knowledge graphs from two types of multi-hop topological structures: (i) by constructing relationship path subgraphs to characterize sets of relation paths between entities and proposing an attention-enhanced recursive message-passing scheme to capture the graph structure within relation paths and their dynamic interactions; and (ii) by integrating the local multi-hop neighbourhood information of entities to capture their intrinsic properties and deep contextual semantics. Experimental results demonstrate that the R-APSC model significantly outperforms state-of-the-art relation prediction models on multiple benchmark datasets, validating the importance of understanding relation semantic propagation and dependencies from a global perspective.