Q-GNN: Query-Conditioned Graph Neural Networks with Type Awareness for Knowledge Graph Completion

2026-06-03

AI Summary

This work addresses the limitation of existing knowledge graph completion methods, which rely solely on query relations during inference and overlook the structural and semantic information inherent in query entities, thereby constraining reasoning performance. To overcome this, the authors propose a novel graph neural network framework that uniquely integrates the local structural context of query entities and their semantic types—derived from large language models—into the message-passing process. Central to this approach is a query-conditioned, type-aware attention mechanism that enables fine-grained, relation- and entity-driven reasoning. Experimental results on standard benchmarks demonstrate that the proposed method significantly outperforms current state-of-the-art techniques, confirming the effectiveness of incorporating multidimensional information from query entities to enhance knowledge graph completion.

Abstract

Knowledge Graph Completion (KGC) aims at predicting missing triplets from incomplete knowledge graphs, which is crucial for downstream applications. Recently, Graph Neural Network (GNN)-based methods have achieved remarkable success by performing message passing over query-centered local subgraphs. However, in practice, a query is jointly defined by both the entity and the relation, with both carrying information indispensable for reasoning, yet these methods rely solely on the query relation as the guiding signal, while the information inherent in the query entity is not leveraged to guide inference - the entity serves merely as a structural anchor for subgraph extraction. To this end, we incorporate query entity information into the reasoning process from two perspectives: the first is structural context, i.e., the neighboring structure and relation patterns around the entity, which is encoded by a dedicated context encoder and used to modulate messages; the second is semantic type of the entity, inferred by a large language model, which is incorporated into attention computation and final scoring to provide type-level prior constraints. Together, these two sources of information enable the reasoning process to be guided by both the query relation and the query entity. Experimental results on standard benchmarks demonstrate the effectiveness of the proposed Q-GNN.

Problem

• Knowledge Graph Completion
• Query Entity
• Graph Neural Networks
• Type Awareness
• Missing Triplets

Innovation

• Query-Conditioned GNN
• Entity-Aware Reasoning
• Structural Context Encoding
• Type-Aware Attention
• Knowledge Graph Completion