DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning

doi:10.1016/j.neunet.2020.11.012

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 类脑认知计算

	DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning
	Tiwari, Prayag 2; Zhu, Hongyin 1; Pandey, Hari Mohan 3
刊名	NEURAL NETWORKS
	2021-03-01
卷号	135 页码:1-12
关键词	Knowledge graph reasoning Reinforcement learning Graph self-attention GRU
ISSN号	0893-6080
DOI	10.1016/j.neunet.2020.11.012
通讯作者	Tiwari, Prayag(prayag.tiwari@dei.unipd.it) ; Pandey, Hari Mohan(pandeyh@edgehill.ac.uk)
英文摘要	Knowledge graph reasoning aims to find reasoning paths for relations over incomplete knowledge graphs (KG). Prior works may not take into account that the rewards for each position (vertex in the graph) may be different. We propose the distance-aware reward in the reinforcement learning framework to assign different rewards for different positions. We observe that KG embeddings are learned from independent triples and therefore cannot fully cover the information described in the local neighborhood. To this effect, we integrate a graph self-attention (GSA) mechanism to capture more comprehensive entity information from the neighboring entities and relations. To let the model remember the path, we incorporate the GSA mechanism with GRU to consider the memory of relations in the path. Our approach can train the agent in one-pass, thus eliminating the pre-training or finetuning process, which significantly reduces the problem complexity. Experimental results demonstrate the effectiveness of our method. We found that our model can mine more balanced paths for each relation. (c) 2020 Elsevier Ltd. All rights reserved.
资助项目	European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie Grant[721321]
WOS研究方向	Computer Science ; Neurosciences & Neurology
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:000610987500001
资助机构	European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie Grant
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/43087]
专题	类脑智能研究中心_类脑认知计算
通讯作者	Tiwari, Prayag; Pandey, Hari Mohan
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Padua, Dept Informat Engn, Padua, Italy 3.Edge Hill Univ, Dept Comp Sci, Ormskirk L39 4QP, England
推荐引用方式 GB/T 7714	Tiwari, Prayag,Zhu, Hongyin,Pandey, Hari Mohan. DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning[J]. NEURAL NETWORKS,2021,135:1-12.
APA	Tiwari, Prayag,Zhu, Hongyin,&Pandey, Hari Mohan.(2021).DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning.NEURAL NETWORKS,135,1-12.
MLA	Tiwari, Prayag,et al."DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning".NEURAL NETWORKS 135(2021):1-12.