BFU: Bayesian Federated Unlearning with Parameter Self-Sharing

As the right to be forgotten has been legislated worldwide, many studies attempt to design machine unlearning mechanisms to enable data erasure from a trained model. Existing machine unlearning studies focus on centralized learning, where the server can access all users' data. However, in a popular scenario, federated learning (FL), the server cannot access users' training data. In this paper, we investigate the problem of machine unlearning in FL. We formalize a federated unlearning problem and propose a bayesian federated unlearning (BFU) approach to implement unlearning for a trained FL model without sharing raw data with the server. Specifically, we first introduce an unlearning rate in BFU to balance the trade-off between forgetting the erased data and remembering the original global model, making it adaptive to different unlearning tasks. Then, to mitigate accuracy degradation caused by unlearning, we propose BFU with parameter self-sharing (BFU-SS). BFU-SS considers data erasure and maintaining learning accuracy as two tasks and optimizes them together during unlearning. Extensive comparisons between our methods and the state-of-art federated unlearning method demonstrate the superiority of our proposed realizations.

Automated summary

As the right to be forgotten is legislated worldwide, there is a need for machine unlearning mechanisms in federated learning scenarios. This paper proposes a Bayesian federated unlearning approach that allows data erasure from a trained model in federated learning without sharing raw data with the server. The proposed approach considers the trade-off between forgetting erased data and preserving the original global model, and mitigates accuracy degradation caused by unlearning.