中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Domain-incremental learning without forgetting based on random vector functional link networks

文献类型：期刊论文

作者Liu, Chong1,2; Wang, Yi1,2; Li, Dong2; Wang, Xizhao3
刊名PATTERN RECOGNITION
出版日期2024-07-01
卷号151页码:12
关键词Incremental learning Domain-incremental learning RVFL network Catastrophic forgetting Privacy preservation
ISSN号0031-3203
DOI10.1016/j.patcog.2024.110430
英文摘要Incremental learning is a paradigm that extends knowledge by learning from new data, often used to add new classes to an existing model or to learn a new domain. It imposes strict limitations on the model's access to data from previous tasks, making it similar to the human learning process. The main challenge of incremental learning is catastrophic forgetting, where previous knowledge is severely forgotten while learning new tasks. In this work, we propose a novel approach for domain -incremental learning. Inspired by the Normal Equation , we accumulate the Gram Matrix from each task's hidden layer output to update a simplified RVFL model. This algorithm achieves performance comparable to joint training while strictly adhering to privacy restrictions. With issues such as forgetting, storage requirements and privacy protection be addressed, this algorithm has the potential to play a crucial role in the field of edge computing and other related fields.
资助项目National Natural Sci-ence Foundation of China[61976141] ; State Key Laboratory of Computer Architecture, ICT, CAS[CARCH5203]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001223736800001
出版者ELSEVIER SCI LTD
源URL[http://119.78.100.204/handle/2XEOYT63/38962]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Xizhao
作者单位1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
3.Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen, Guangdong, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Chong,Wang, Yi,Li, Dong,et al. Domain-incremental learning without forgetting based on random vector functional link networks[J]. PATTERN RECOGNITION,2024,151:12.
APA Liu, Chong,Wang, Yi,Li, Dong,&Wang, Xizhao.(2024).Domain-incremental learning without forgetting based on random vector functional link networks.PATTERN RECOGNITION,151,12.
MLA Liu, Chong,et al."Domain-incremental learning without forgetting based on random vector functional link networks".PATTERN RECOGNITION 151(2024):12.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。