Communication Dans Un Congrès Année : 2024

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

Résumé

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending MU to unlearn a given client's contribution from a federated training routine. While several FU methods have been proposed, we currently lack a general approach providing formal unlearning guarantees to the FedAvg routine, while ensuring scalability and generalization beyond the convex assumption on the clients' loss functions. We aim at filling this gap by proposing SIFU (Sequential Informed Federated Unlearning), a new FU method applying to both convex and non-convex optimization regimes. SIFU naturally applies to FedAvg without additional computational cost for the clients and provides formal guarantees on the quality of the unlearning task. We provide a theoretical analysis of the unlearning properties of SIFU, and practically demonstrate its effectiveness as compared to a panel of unlearning methods from the state-of-the-art.

Fichier principal
Vignette du fichier
2211.11656v5.pdf (1.18 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04839304 , version 1 (20-01-2025)

Licence

Identifiants

Citer

Yann Fraboni, Martin van Waerebeke, Richard Vidal, Laetitia Kameni, Kevin Scaman, et al.. SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization. AISTATS 2024 - International Conference on Artificial Intelligence and Statistics, May 2024, Valencia, Spain. ⟨hal-04839304⟩
228 Consultations
262 Téléchargements

Altmetric

Partager

  • More