Aug 2026· 2026 12th International Conference on Big Data and Information Analytics (BigDIA)· pp. 1090-1097· 0 citations· 26 references
Abstract
Client-level federated unlearning seeks to update an already trained global model so that the influence of a specified client is weakened, while the model remains effective for the remaining clients. Existing methods are mostly designed for homogeneous model settings and often rely on retraining, historical updates, or direct gradient reversal, making them less suitable for clients with heterogeneous computational capacities. This paper studies client-level unlearning in heterogeneous multi-exit federated learning, where clients participate with different model depths. We propose FedDRU, a depth-aware residual unlearning method that uses retained-client directions to represent shared knowledge, decomposes the target-client update into shared and residual components, and reverses only the residual contribution with a lightweight confidence softening constraint. Experiments on CIFAR-10 and CIFAR-100 with three-exit ResNet and ViT models show that FedDRU effectively suppresses target-client influence while maintaining competitive retained-client accuracy, achieving a stable trade-off between forgetting effectiveness and retained-client utility.
To remove the contribution of specific data from the global model in federated learning, federated unlearning has recently emerged. Existing approaches face challenges such as reliance on full client participation, the need to store historical model updates, and high communication costs. To overcome these limitations,...
Lei Tian, Fei-Long Lin, Zhan Qin et al.· IEEE Transactions on Informa...· 0 citations
Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space using an NTK-based agreement score to characterize predictive behavior and determine a persona...
Mirko Konstantin, S. Zachow, Anirban Mukhopadhyay· 0 citations
This paper considers the practical setting where the learner keeps a small proxy dataset, and proposes a dynamic, influence-aware client selection framework that estimates each client's potential utility to the learner's optimization objective using proxy influence signals on a learner-specific proxy set.
Yi-Ming Xie, Linghui Su, Ning-Fang Mi· 0 citations
This work proposes SAPE-FL (Similarity-Aware Personalized Federated Learning), a novel personalization framework that anchors each client's model to both the global model and a similarity-weighted peer averaged model that mitigates negative transfer and enhances robustness in heterogeneous settings.
V. ArunKumarA, Sunil Gupta, Ngyuen Dang et al.· 0 citations
A client-specific adaptation channel based on private prompt tokens, which tracks local adaptation dynamics separately from the shared backbone and provides a lightweight signal for detecting whether client adaptation remains active, and a shallow sufficiency estimator that combines cross-client semantic alignment, tem...
Wen-Hao Yuan, Chen-Chen Lin, Wentao Hu et al.· 0 citations
Driven by privacy regulations, federated unlearning (FU) aims to remove the influence of specific clients or samples from a trained federated model, approximating the behavior of retraining from scratch without the target data. However, existing FU methods are largely reactive: retraining-based solutions are accurate b...
Jin-Shan Lai, Feng-Chun Zhang, Yun-Yuan Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
