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

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

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.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages11096-11100
Number of pages5
ISBN (Electronic)9798350344851
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/2419/04/24

Keywords

  • Multi-hop knowledge reasoning
  • Multimodal knowledge graph

Cite this