Not All Retained Clients Are Equal: Client Selection for Federated Unlearning

A new arXiv paper (2610.31786v1) introduces PDF, a path-dependent client-selection framework for federated unlearning that ranks retained clients by critical-learning-period-weighted histories rather than treating all retained clients as equally valuable. On non-IID CIFAR-10, PDF reached 0% forgetting accuracy with retraining-like membership inference attack AUC, improved retained accuracy by up to 6.91 percentage points over the strongest competing federated unlearning baseline on CIFAR-100, and cut communication by roughly 69% and computation by 57–61% relative to full retraining. The authors report results on FMNIST, CIFAR-10 and CIFAR-100 under both IID and non-IID settings.

arXiv:2610.31786v1 Announce Type: new Abstract: Federated unlearning FU aims to remove a designated target client's influence from a trained model without the prohibitive cost of retraining from scratch. Existing methods largely treat unlearning as a post-hoc, stateless operation, overlooking that client influence is path-dependent: contributions made during training, particularly during critical learning periods CLPs , can have disproportionate and persistent effects. Moreover, knowledge overlap and intermittent client availability make relying on all retained clients inefficient and impractical. We introduce PDF, a path-dependent client-selection framework based on the insight that retained clients are not equally valuable for unlearning. During training, PDF maintains lightweight, target-agnostic, CLP-weighted histories summarizing each client's accumulated update direction and global-model alignment. Upon an unlearning request, these histories identify and rank retained clients that are globally informative yet weakly coupled to the target, enabling retraining-based unlearning with only the top-$k$ clients over a small number of rounds. Experiments on FMNIST, CIFAR-10, and CIFAR-100 under IID and non-IID settings show that PDF achieves effective forgetting and strong retained utility with substantially fewer retained clients. In particular, PDF achieves $0\%$ forgetting accuracy with retraining-like MIA AUC on non-IID CIFAR-10, improves retained accuracy by up to $6.91$ percentage points over the strongest competing FU baseline on CIFAR-100, and reduces communication by approximately $69\%$ and computation by $57$--$61\%$ relative to Retrain.