Abstract:Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearning (FU) has emerged to address the "right to be forgotten" and to remove the influence of poisoned or target clients without retraining the entire FL system. However, many FU methods require communication with retained or target clients, introduce additional security risks, or store historical models, limiting their efficiency and practicality. Moreover, most FU methods for deep neural networks (DNNs) lack theoretical certification due to the complexity of nonlinear models and their training dynamics. In this work, we introduce Forgettable Federated Linear Learning, a training and unlearning framework for DNNs. Our approach uses pre-trained models to linearly approximate DNNs and achieve performance comparable to the original networks through Federated Linear Training. We further present a certified, efficient, and secure unlearning strategy that enables the server to remove a target client's influence without additional client communication or storage. Extensive experiments on small- to large-scale datasets, using both convolutional neural networks and modern foundation models, show that our method balances model accuracy with effective target-client unlearning. This work provides a practical pipeline for efficient and trustworthy FU. Code: this https URL
| Comments: | IEEE Transactions on Neural Networks and Learning Systems |
| Subjects: | Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2306.02216 [cs.LG] |
| (or arXiv:2306.02216v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2306.02216 arXiv-issued DOI via DataCite |
|
| Journal reference: | IEEE Transactions on Neural Networks and Learning Systems, Early Access, pp. 1-10, 2026 |
| Related DOI: | https://doi.org/10.1109/TNNLS.2026.3683398
DOI(s) linking to related resources |
From: Ruinan Jin [view email]
[v1]
Sat, 3 Jun 2023 23:53:57 UTC (359 KB)
[v2]
Tue, 22 Oct 2024 02:33:25 UTC (1,587 KB)
[v3]
Sun, 24 May 2026 17:58:44 UTC (1,749 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。