Federated Unlearning: How to Efficiently Erase a Client in FL?

TL;DR

This paper introduces an efficient federated unlearning method that removes a client's influence from a global model without requiring full retraining or access to all training data, addressing privacy rights and efficiency.

Contribution

It proposes a novel federated unlearning approach combining local unlearning and minimal rounds of federated learning, without needing data access or update history.

Findings

Achieves comparable accuracy to retraining from scratch

Significantly reduces computational cost

Does not require global data access or update history

Abstract

With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a client, we propose to first perform local unlearning at the client to be erased, and then use the locally unlearned model as the initialization to run very few rounds of federated learning between the server and the remaining clients to obtain the unlearned global model. We empirically evaluate our unlearning method by employing multiple performance measures on three datasets, and demonstrate that our unlearning method achieves comparable performance as the gold standard unlearning method of federated retraining from scratch, while being significantly efficient. Unlike prior works, our unlearning method neither requires global access to the data used for training nor the history of the parameter updates to be stored by the server or any of the clients.