MHPS: Multimodality-Guided Hierarchical Policy Search for Knowledge Graph Reasoning
Chen Gao, Xugong Qin, Peng Zhang, Yongquan He, Xinjian Huang, Ming Zhou, Liehuang Zhu, Qingfeng Tan
Abstract
Recently, path inference-based knowledge graph reasoning (KGR) methods have attracted great attention due to their good performance and interpretability. However, as the number of hops increases, the search space grows exponentially, making the reward sparse and the process of reasoning difficult. To alleviate this problem, we propose the Multimodality-guided Hierarchical Policy Search (MHPS) for KGR, which introduces multimodal hierarchical guidance to each layer of policies during policy search. On the one hand, multimodal guidance reserves rich information on different dimensions, providing more opportunities to find better paths. On the other hand, this leads to better interaction between the two agents, resulting in more concise guidance for policy stepping. Experimental results on two public datasets demonstrate that the proposed approach outperforms state-of-the-art methods on multi-hop KGR.
BibTeX
@inproceedings{icassp2024_mhpsmultimodalit,
title = {MHPS: Multimodality-Guided Hierarchical Policy Search for Knowledge Graph Reasoning},
author = {Chen Gao and Xugong Qin and Peng Zhang and Yongquan He and Xinjian Huang and Ming Zhou and Liehuang Zhu and Qingfeng Tan},
booktitle = {ICASSP 2024},
year = {2024}
}