No One Left Behind: Real-World Federated Class-Incremental Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-04 · 46 (4) · 2054-2070
DOI: 10.1109/tpami.2023.3334213 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-04. Verfasst von Jiahua Dong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 83-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Robotics.
Abstract (Originalsprache)
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods.
Förderung
- National Natural Science Foundation of China
- State Key Laboratory of Robotics
Zitieren
APA
Dong, J., Li, H., Cong, Y., Sun, G., Zhang, Y., & Gool, L. V. (2024). No One Left Behind: Real-World Federated Class-Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 2054-2070. https://doi.org/10.1109/tpami.2023.3334213
Vancouver
Dong J, Li H, Cong Y, Sun G, Zhang Y, Gool LV. No One Left Behind: Real-World Federated Class-Incremental Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(4):2054-2070. doi:10.1109/tpami.2023.3334213
BibTeX
@article{Dong2024,
author = {Dong, Jiahua and Li, Hongliu and Cong, Yang and Sun, Gan and Zhang, Yulun and Gool, Luc Van},
title = {No One Left Behind: Real-World Federated Class-Incremental Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {4},
pages = {2054--2070},
doi = {10.1109/tpami.2023.3334213}
}
EUVIMED