Metraipolis › archive › dc_53e151a12ae7
Not All Retained Clients Are Equal: Client Selection for Federated Unlearning — arXiv:2610.31786
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31786
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:54:39.551Z
- SHA-256 of the archived text
2223fce51cd00d163a17916d1558713a270bf7893216ca3eacd77a9a02040a69- Stable URL of this page
https://metraipolis.com/documento/dc_53e151a12ae7
How to cite
Not All Retained Clients Are Equal: Client Selection for Federated Unlearning — arXiv:2610.31786 — arXiv (en), https://arxiv.org/abs/2610.31786 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53e151a12ae7 (Metraipolis archive dc_53e151a12ae7, sha256 2223fce51cd00d163a17916d1558713a270bf7893216ca3eacd77a9a02040a69)
BibTeX
@misc{dc53e151a12ae7,
title = {Not All Retained Clients Are Equal: Client Selection for Federated Unlearning — arXiv:2610.31786},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31786},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53e151a12ae7; sha256 2223fce51cd00d163a17916d1558713a270bf7893216ca3eacd77a9a02040a69},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31786. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Distributed, Parallel, and Cluster Computing (cs.DC); Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2610.31786 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-26T19:46:03.301Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).