Federated Class-Incremental Learning with New-Class Augmented Self-Distillation
文献类型：期刊论文
| 作者 | Wu, Zhi-Yuan2,3; Sun, Sheng2,3; He, Tian-Liu2; Wang, Yu-Wei2; Liu, Min1,2; Gao, Bo4; Jiang, Xue-Feng2,3 |
| 刊名 | JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
 |
| 出版日期 | 2025-09-01 |
| 卷号 | 40期号:5页码:1427-1437 |
| 关键词 | federated learning class-incremental learning knowledge distillation |
| ISSN号 | 1000-9000 |
| DOI | 10.1007/s11390-025-5186-5 |
| 英文摘要 | Federated learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify in classes over time. This oversight results in FL methods suffering from catastrophic forgetting, where the trained models inadvertently discard previously learned information upon assimilating new data. In response to this challenge, we propose a novel federated class-incremental learning (FCIL) method, named Federated Class-incremental Learning with New-Class Augmented Self-Distillation (FedCLASS). The core of FedCLASS is to enrich the class scores of historical models with new class scores predicted by current models and utilize the combined knowledge for self-distillation, enabling a more sufficient and precise knowledge transfer from historical models to current models. Theoretical analyses demonstrate that FedCLASS stands on reliable foundations, considering the scores of old classes predicted by historical models as conditional probabilities in the absence of new classes, and the scores of new classes predicted by current models as the conditional probabilities of class scores derived from historical models. Empirical experiments demonstrate the superiority of FedCLASS over four baseline algorithms in reducing average forgetting rate and boosting global accuracy. |
| 资助项目 | National Key Research and Development Program of China[2023YFB2703700] ; National Natural Science Foundation of China[62472410] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001621167000004 |
| 出版者 | SPRINGER SINGAPORE PTE LTD |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/43077]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Wang, Yu-Wei |
| 作者单位 | 1.Zhongguancun Lab, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 4.Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wu, Zhi-Yuan,Sun, Sheng,He, Tian-Liu,et al. Federated Class-Incremental Learning with New-Class Augmented Self-Distillation[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2025,40(5):1427-1437. |
| APA | Wu, Zhi-Yuan.,Sun, Sheng.,He, Tian-Liu.,Wang, Yu-Wei.,Liu, Min.,...&Jiang, Xue-Feng.(2025).Federated Class-Incremental Learning with New-Class Augmented Self-Distillation.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,40(5),1427-1437. |
| MLA | Wu, Zhi-Yuan,et al."Federated Class-Incremental Learning with New-Class Augmented Self-Distillation".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 40.5(2025):1427-1437. |
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。