Re-Fed+: A Better Replay Strategy for Federated Incremental Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 5489-5500
DOI: 10.1109/tpami.2025.3551732 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Yichen Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Major Science and Technology Project of Hubei Province.
Abstract (Originalsprache)
Federated learning (FL) has emerged as a significant distributed machine learning paradigm. It allows the training of a global model through user collaboration without the necessity of sharing their original data. Traditional FL generally assumes that each client's data remains fixed or static. However, in real-world scenarios, data typically arrives incrementally, leading to a dynamically expanding data domain. In this study, we examine catastrophic forgetting within Federated Incremental Learning (FIL) and focus on the training resources, where edge clients may not have sufficient storage to keep all data or computational budget to implement complex algorithms designed for the server-based environment. We propose a general and low-cost framework for FIL named Re-Fed+, which is designed to help clients cache important samples for replay. Specifically, when a new task arrives, each client initially caches selected previous samples based on their global and local significance. The client then trains the local model using both the cached samples and the new task samples. From a theoretical perspective, we analyze how effectively Re-Fed+ can identify significant samples for replay to alleviate the catastrophic forgetting issue. Empirically, we show that Re-Fed+ achieves competitive performance compared to state-of-the-art methods.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Major Science and Technology Project of Hubei Province
- Hubei Science and Technology
- Ant Group through CCF-Ant Research Fund
Zitieren
APA
Li, Y., Wang, H., Qi, Y., Liu, W., & Li, R. (2025). Re-Fed+: A Better Replay Strategy for Federated Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 5489-5500. https://doi.org/10.1109/tpami.2025.3551732
Vancouver
Li Y, Wang H, Qi Y, Liu W, Li R. Re-Fed+: A Better Replay Strategy for Federated Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):5489-5500. doi:10.1109/tpami.2025.3551732
BibTeX
@article{Li2025,
author = {Li, Yichen and Wang, Haozhao and Qi, Yining and Liu, Wei and Li, Ruixuan},
title = {Re-Fed+: A Better Replay Strategy for Federated Incremental Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {7},
pages = {5489--5500},
doi = {10.1109/tpami.2025.3551732}
}
EUVIMED