STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation

Exploring foci of: arXiv (Cornell University) STSA: Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregation June 2025 • Zhenzhen Guan, Guojun Zhu, Zhou Yucan, Wu Liu, Weiping Wang, Jiebo Luo, Xiaoyan Gu Federated Class-Incremental Learning (FCIL) enables Class-Incremental Learning (CIL) from distributed data. Existing FCIL methods typically integrate old knowledge preservation into local client training. However, these methods cannot avoid spatial-temporal client drift caused by data heterogeneity and often incur significant computational and communication overhead, limiting practical deployment. To address these challenges simultaneously, we propose a novel approach, Spatial-Temporal Statistics Aggregation (STSA… Open Article Page

Learning Curve Learning Theory (Education) Experiential Learning Practice (Learning Method) Learning Environment Machine Learning List Of Real Madrid Cf Records And Statistics Iga Świątek Career Statistics Federated States Of Micronesia Open Article

Statistics Deep Learning Reinforcement Learning Learning Standards Novak Djokovic Career Statistics Carlos Alcaraz Career Statistics Attention (Machine Learning) Jessica Pegula Career Statistics Rafael Nadal Career Statistics Open Article

Learning Federated State List Of Liverpool F.C. Records And Statistics Jannik Sinner Career Statistics Learning Disability Decision Tree Learning Open Article