Graph meets probabilistic generation model: A new perspective for graph disentanglement

doi:10.1016/j.patcog.2023.110153

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统认知与决策实验室

	Graph meets probabilistic generation model: A new perspective for graph disentanglement
	Peng, Zouzhang 1,2; Zheng, Shuai 1,2; Zhu, Zhenfeng 1,2; Liu, Zhizhe 1,2; Cheng, Jian 3; Dong, Honghui 4; Zhao, Yao 1,2
刊名	PATTERN RECOGNITION
	2024-04-01
卷号	148 页码:11
关键词	Graph representation learning Graph disentanglement Probabilistic generation model
ISSN号	0031-3203
DOI	10.1016/j.patcog.2023.110153
通讯作者	Peng, Zouzhang(pengzouzhang@bjtu.edu.cn) ; Zheng, Shuai(zs1997@bjtu.edu.cn) ; Zhu, Zhenfeng(zhfzhu@bjtu.edu.cn)
英文摘要	Different from the existing graph disentanglement neural networks, we interpret the graph entanglement under a probabilistic generation framework in this paper. With this foundation, a Mixed Probabilistic Generation Model induced Graph Disentanglement Network (MPGD) is proposed. Considering the disentangled components corresponding to different factors as obeying specific distributions, a generalized probabilistic aggregation scheme among components is deduced theoretically. As a key part of the mixed probabilistic generative model, we provide a solution for estimating the mixture probabilities using self-attention and an in-depth analysis of its close connection with the classical EM parameter estimation method. Meanwhile, a way of probabilistic aggregation is formulated to obtain the node representation in embedding space. In addition, the prior mixture probabilities are formulated as an auxiliary factor-aware representation to facilitate the twin branch prediction. A variety of experiments show that MPGD achieves more competitive performance than some existing state-of-the-art methods while having ideal disentangling effects. The code implementation is available in https://github.com/GiorgioPeng/MPGD.
资助项目	National Natural Science Foundation of China[2018AAA0102101] ; [61976018]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:001128636200001
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54946]
专题	复杂系统认知与决策实验室
通讯作者	Peng, Zouzhang; Zheng, Shuai; Zhu, Zhenfeng
作者单位	1.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China 2.Network Technol, Beijing Key Lab Adv Informat Sci, Beijing 100044, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Beijing Jiaotong Univ, Sch Traff & Transportat, Beijing 100044, Peoples R China
推荐引用方式 GB/T 7714	Peng, Zouzhang,Zheng, Shuai,Zhu, Zhenfeng,et al. Graph meets probabilistic generation model: A new perspective for graph disentanglement[J]. PATTERN RECOGNITION,2024,148:11.
APA	Peng, Zouzhang.,Zheng, Shuai.,Zhu, Zhenfeng.,Liu, Zhizhe.,Cheng, Jian.,...&Zhao, Yao.(2024).Graph meets probabilistic generation model: A new perspective for graph disentanglement.PATTERN RECOGNITION,148,11.
MLA	Peng, Zouzhang,et al."Graph meets probabilistic generation model: A new perspective for graph disentanglement".PATTERN RECOGNITION 148(2024):11.