Hierarchical Multihop Reasoning on Knowledge Graphs

Multihop knowledge reasoning aims to find missing entities for incomplete triples by finding paths on knowledge graphs. It is a fundamental and important task. In this article, we devise a hierarchical reinforcement learning algorithm to model the reasoning process more effectively. Unlike existing methods directly reason on entities and relations, we adopt a high-level reasoning layer to deal with abstract concepts, which guides the reasoning process conducted at the low level for concrete entities and relations. Our approach yields competitive results on link prediction on both NELL-995 and FB15k-237 datasets. The comparison to baselines also demonstrates the effectiveness of the hierarchical structure.

Automated summary

Multihop knowledge reasoning is a fundamental and important task to find missing entities for incomplete triples by finding paths on knowledge graphs. In this article, a hierarchical reinforcement learning algorithm is devised to model the reasoning process effectively. By incorporating a high-level reasoning layer to handle abstract concepts and guiding the low-level reasoning process for concrete entities and relations, the proposed approach achieves competitive results on link prediction tasks and demonstrates the effectiveness of the hierarchical structure.