Leveraging maximum entropy and correlation on latent factors for learning representations

doi:10.1016/j.neunet.2020.07.027

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Leveraging maximum entropy and correlation on latent factors for learning representations
	He, Zhicheng 1; Liu, Jie 1; Dang, Kai 1; Zhuang, Fuzhen 2,3; Huang, Yalou 4
刊名	NEURAL NETWORKS
	2020-11-01
卷号	131 页码:312-323
关键词	Non-negative Matrix Factorization Maximum entropy Correlated latent factor learning
ISSN号	0893-6080
DOI	10.1016/j.neunet.2020.07.027
英文摘要	Many tasks involve learning representations from matrices, and Non-negative Matrix Factorization (NMF) has been widely used due to its excellent interpretability. Through factorization, sample vectors are reconstructed as additive combinations of latent factors, which are represented as non-negative distributions over the raw input features. NMF models are significantly affected by latent factors' distribution characteristics and the correlations among them. And NMF models are faced with the challenge of learning robust latent factor. To this end, we propose to learn representations with an awareness of the semantic quality evaluated from the aspects of intra- and inter-factors. On the one hand, a Maximum Entropy-based function is devised for the intra-factor semantic quality. On the other hand, the semantic uniqueness is evaluated via inter-factor correlation, which reinforces the aim of semantic compactness. Moreover, we present a novel non-linear NMF framework. The learning algorithm is presented and the convergence is theoretically analyzed and proved. Extensive experimental results on multiple datasets demonstrate that our method can be successfully applied to representative NMF models and boost performances over state-of-the-art models. (C) 2020 Elsevier Ltd. All rights reserved.
资助项目	National Natural Science Foundation of China[61976119] ; Science and Technology Planning Project of Tianjin, China[18ZXZNGX00310]
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:000581746300025
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/15474]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Jie
作者单位	1.Nankai Univ, Coll Artificial Intelligence, Tianjin, Peoples R China 2.Chinese Acad Sci, Xiamen Data Intelligence Acad ICT, Xiamen, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 4.Nankai Univ, Coll Software, Tianjin, Peoples R China
推荐引用方式 GB/T 7714	He, Zhicheng,Liu, Jie,Dang, Kai,et al. Leveraging maximum entropy and correlation on latent factors for learning representations[J]. NEURAL NETWORKS,2020,131:312-323.
APA	He, Zhicheng,Liu, Jie,Dang, Kai,Zhuang, Fuzhen,&Huang, Yalou.(2020).Leveraging maximum entropy and correlation on latent factors for learning representations.NEURAL NETWORKS,131,312-323.
MLA	He, Zhicheng,et al."Leveraging maximum entropy and correlation on latent factors for learning representations".NEURAL NETWORKS 131(2020):312-323.