Federated Learning (FL) systems enable the collaborative training of machine learning models without requiring centralized collection of individual data. FL participants should have the ability to exercise their right to be forgotten, ensuring their past contributions can be removed from the learned model upon request. In this paper, we propose FedQUIT, a novel algorithm that uses knowledge distillation to scrub the contribution of the data to forget from an FL global model while preserving its generalization ability. FedQUIT directly works on client devices that request to leave the federation, and leverages a teacher-student framework. The FL global model acts as the teacher, and the local model works as the student. To induce forgetting, FedQUIT tailors the teacher's output on local data (the data to forget) penalizing the prediction score of the true class. Unlike previous work, our method does not require hardly viable assumptions for cross-device settings, such as storing historical updates of participants or requiring access to proxy datasets. Experimental results on various datasets and model architectures demonstrate that (i) FedQUIT outperforms state-of-the-art competitors in forgetting data, (ii) has the exact computational requirements as a regular FedAvg round, and (iii) reduces the cumulative communication costs by up to 117.6 compared to retraining from scratch to restore the initial generalization performance after unlearning.
View on arXiv@article{mora2025_2408.07587,
title={ FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher },
author={ Alessio Mora and Lorenzo Valerio and Paolo Bellavista and Andrea Passarella },
journal={arXiv preprint arXiv:2408.07587},
year={ 2025 }
}