FedUNRAN: On-device Federated Unlearning via Random Labels
Alessio Mora, Luca Dominici, Paolo Bellavista · 2024
In Federated Learning, a group of devices collaboratively learns a global machine learning model by periodically transferring locally computed model updates. This approach ensures the privacy of local data and encourages broader participation. However, as required by regulations such as the General Data Protection Regulation (GDPR), when a participating device decides to withdraw its contribution, FL systems must remove its data from the global model. In this paper, we introduce FedUNRAN, a novel and practical method to efficiently remove the contribution of an FL client from the global model without requiring retraining from scratch. Our method allows the requesting client to perform the unlearning procedure locally. FedUNRAN is lightweight, maintains the privacy-focused structure of FL, and enables effective client-side unlearning. We conduct an empirical evaluation of the method against the natural baseline, which involves simply detaching the unlearning client from training. Our results demonstrate that FedUNRAN is effective and efficient. Our code is available at: https://github.com/alessiomora/FedUNRAN