Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
Abstract
The advent of Federated Learning (FL) highlights the practical necessity for the right to be forgotten for all clients, allowing them to request data deletion from the machine learning models service provider. This necessity has spurred a growing demand for Federated Unlearning (FU). Feature unlearning has gained considerable attention due to its applications in unlearning sensitive, backdoor, and biased features. Existing methods employ the influence function to achieve feature unlearning, which is impractical for FL as it necessitates the participation of other clients, if not all, in the unlearning process. Furthermore, current research lacks an evaluation of the effectiveness of feature unlearning. To address these limitations, we define feature sensitivity in evaluating feature unlearning according to Lipschitz continuity. This metric characterizes the model outputs rate of change or sensitivity to perturbations in the input feature. We then propose an effective federated feature unlearning framework called Ferrari, which minimizes feature sensitivity. Extensive experimental results and theoretical analysis demonstrate the effectiveness of Ferrari across various feature unlearning scenarios, including sensitive, backdoor, and biased features. The code is publicly available at https://github.com/OngWinKent/Federated-Feature-Unlearning
Cite
@article{arxiv.2405.17462,
title = {Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity},
author = {Hanlin Gu and Win Kent Ong and Chee Seng Chan and Lixin Fan},
journal= {arXiv preprint arXiv:2405.17462},
year = {2025}
}
Comments
TLDR: The need for a "right to be forgotten" in Federated Learning has led to the development of the Ferrari framework, which efficiently unlearns sensitive features using a Lipschitz continuity-based metric, proven effective in extensive testing. Accepted at NeurIPS 2024