Dual view graph transformer networks for multi-hop knowledge graph reasoning

Abstract

To address the incompleteness of knowledge graphs, multi-hop reasoning aims to find the unknown information from existing data and enhance the comprehensive understanding. The presence of reasoning paths endows multi-hop reasoning with interpretability and traceability. Existing reinforcement learning (RL)-based multi-hop reasoning methods primarily rely on the agent’s blind trial-and-error approach in a large search space, which leads to inefficient training. In contrast, sequence-based multi-hop reasoning methods focus on learning the mapping from path to path to achieve better training efficiency, but they discard structured knowledge. The absence of structured knowledge directly hinders the ablity to capture and represent complex relations. To address the above issues, we propose a Dual View Graph Transformer Networks for Multi-hop Knowledge Graph Reasoning (DV4KGR), which enables the joint learning of structured and serialized views. The structured view contains a large amount of structured knowledge, which represents the relations among nodes from a global perspective. Meanwhile, the serialized view contains rich knowledge of reasoning semantics, aiding in training the mapping function from reasoning states to reasoning paths. We learn the representations of one-to-many relations in a supervised contrastive learning manner, which enhances the ability to represent complex relations. Additionally, we combine structured knowledge and rule induction for action smoothing, which effectively alleviates the overfitting problem associated with the end-to-end training mode. The experimental results on four benchmark datasets demonstrate that DV4KGR delivers better performance than the state-of-the-art baselines.