Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods

doi:10.1109/ACCESS.2020.3028067

	Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods
	Chang, Yifan 2,3; Li, Wenbo 3; Peng, Jian 1; Li, Haifeng 1; Kang, Yu 2; Huang, Yingliang 4
刊名	IEEE ACCESS
	2020
卷号	8
关键词	Gallium nitride Task analysis Generators Generative adversarial networks Training Neural networks Knowledge engineering Catastrophic forgetting generative adversarial network parameter regularization methods
ISSN号	2169-3536
DOI	10.1109/ACCESS.2020.3028067
通讯作者	Kang, Yu(kangduyu@ustc.edu.cn)
英文摘要	Generative adversarial networks (GANs) suffer from catastrophic forgetting when learning multiple consecutive tasks. Parameter regularization methods that constrain the parameters of the new model in order to be close to the previous model through parameter importance are effective in overcoming forgetting. Many parameter regularization methods have been tried, but each of them is only suitable for limited types of neural networks. Aimed at GANs, this paper proposes a unified framework called Memory Protection GAN (MPGAN), in which many parametrization methods can be used to overcome forgetting. The proposed framework includes two modules: Protecting Weights in Generator and Controller. In order to incorporate parameter regularization methods into MPGAN, the Protecting Weights in Generator module encapsulates different parameter regularization methods into a "container", and consolidates the most important parameters in the generator through a parameter regularization method selected from the container. In order to differentiate tasks, the Controller module creates unique tags for the tasks. Another problem with existing parameter regularization methods is their low accuracy in measuring parameter importance. These methods always rely on the first derivative of the output function, and ignore the second derivative. To assess parameter importance more accurately, a new parameter regularization method called Second Derivative Preserver (SDP), which takes advantage of the second derivative of the output function, is designed into MPGAN. Experiments demonstrate that MPGAN is applicable to multiple parameter regularization methods and that SDP achieves high accuracy in parameter importance.
资助项目	Development Program of China[2018YFB1004600] ; Development Program of China[2017YFC1503000] ; National Nature Science Foundation of China[41701594] ; National Nature Science Foundation of China[41871302]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000576765700001
资助机构	Development Program of China ; National Nature Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/104461]
专题	中国科学院合肥物质科学研究院
通讯作者	Kang, Yu
作者单位	1.Cent South Univ, Sch Geosci & Infophys, Changsha 410083, Peoples R China 2.Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China 3.Chinese Acad Sci, Hefei Inst Phys Sci, Inst Technol Innovat, Hefei 230088, Peoples R China 4.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China
推荐引用方式 GB/T 7714	Chang, Yifan,Li, Wenbo,Peng, Jian,et al. Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods[J]. IEEE ACCESS,2020,8.
APA	Chang, Yifan,Li, Wenbo,Peng, Jian,Li, Haifeng,Kang, Yu,&Huang, Yingliang.(2020).Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods.IEEE ACCESS,8.
MLA	Chang, Yifan,et al."Memory Protection Generative Adversarial Network (MPGAN): A Framework to Overcome the Forgetting of GANs Using Parameter Regularization Methods".IEEE ACCESS 8(2020).