Incremental Concept Learning via Online Generative Memory Recall

doi:10.1109/TNNLS.2020.3010581

	Incremental Concept Learning via Online Generative Memory Recall
	Li, Huaiyu1,2 ; Dong, Weiming1 ; Hu, Bao-Gang1
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2021-07-01
卷号	32 期号:7 页码:3206-3216
通讯作者	Dong, Weiming(weiming.dong@ia.ac.cn)
摘要	The ability to learn more concepts from incrementally arriving data over time is essential for the development of a lifelong learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as the catastrophic forgetting problem. The main reason for catastrophic forgetting is that past concept data are not available, and neural weights are changed during incrementally learning new concepts. In this article, we propose an incremental concept learning framework that includes two components, namely, ICLNet and RecallNet. ICLNet, which consists of a trainable feature extractor and a dynamic concept memory matrix, aims to learn new concepts incrementally. We propose a concept-contrastive loss to alleviate the magnitude of neural weight changes and mitigate the catastrophic forgetting problems. RecallNet aims to consolidate old concepts memory and recall pseudo samples, whereas ICLNet learns new concepts. We propose a balanced online memory recall strategy to reduce the information loss of old concept memory. We evaluate the proposed approach on the MNIST, Fashion-MNIST, and SVHN data sets and compare it with other pseudorehearsal-based approaches. Extensive experiments demonstrate the effectiveness of our approach.
关键词	Task analysis Learning systems Neural networks Feature extraction Visualization Knowledge engineering Training Catastrophic forgetting continual learning generative adversarial networks (GANs)
DOI	10.1109/TNNLS.2020.3010581
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2018AAA0101005] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[61672520] ; National Natural Science Foundation of China[61720106006]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000670541500033
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	机器学习
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/45281
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Dong, Weiming
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Li, Huaiyu,Dong, Weiming,Hu, Bao-Gang. Incremental Concept Learning via Online Generative Memory Recall[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(7):3206-3216.
APA	Li, Huaiyu,Dong, Weiming,&Hu, Bao-Gang.(2021).Incremental Concept Learning via Online Generative Memory Recall.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(7),3206-3216.
MLA	Li, Huaiyu,et al."Incremental Concept Learning via Online Generative Memory Recall".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.7(2021):3206-3216.