Subgraph-centric multi-agent reinforcement learning for multi-hop knowledge graph reasoning
Publication Type
Journal Article
Publication Date
2-2026
Abstract
Multi-hop Knowledge Graph Reasoning (KGR) seeks to identify accurate answers within Knowledge Graphs (KGs) via multi-step reasoning, predominantly utilizing reinforcement learning (RL) to enhance the efficiency of the reasoning process. Unlike traditional Knowledge Graph Embedding (KGE) methods, RL-based approaches offer superior interpretability. However, these methods often underperform due to two critical limitations: (1) their over-reliance on Horn rules for reasoning paths, which restricts their expressive power; and (2) inadequate utilization of reasoning states during the process. To address these issues, we propose a novel RL-based framework, RAR, which shifts focus from individual paths to subgraph structures for more robust predictions. RAR frames the retrieval of reasoning subgraphs from the KG as a Markov Decision Process (MDP) and incorporates a subgraph retriever. To efficiently explore the extensive subgraph space, we integrate multi-agent RL to enhance the retriever’s capabilities. Additionally, RAR features an advanced analyst module that meticulously examines reasoning states. These modules function iteratively: the retriever expands the subgraph, followed by the analyst module’s in-depth analysis. The insights gained are then used to inform subsequent retrieval steps. Ultimately, the predicted scores from both modules are synthesized to produce more precise posterior scores. Experimental results across multiple datasets demonstrate RAR’s efficacy, showcasing a notable improvement over existing state-of-the-art RL-based KGR methods.
Keywords
Knowledge graph reasoning, knowledge graph completion, subgraph reasoning, reinforcement learning
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Intelligent Systems and Optimization
Publication
IEEE Transactions on Knowledge and Data Engineering
Volume
38
Issue
2
First Page
1319
Last Page
1333
ISSN
1041-4347
Identifier
10.1109/TKDE.2025.3631495
Publisher
Institute of Electrical and Electronics Engineers
Citation
HE, Tao; CHEN, Zerui; LIAO, Lizi; CAO, Yixin; LIU, Yuanxing; TANG, Wei; MAO, Xun; and QIN, Bing.
Subgraph-centric multi-agent reinforcement learning for multi-hop knowledge graph reasoning. (2026). IEEE Transactions on Knowledge and Data Engineering. 38, (2), 1319-1333.
Available at: https://ink.library.smu.edu.sg/sis_research/11258
Additional URL
https://doi.org/10.1109/TKDE.2025.3631495