Goldfish: An Efficient Federated Unlearning Framework

TL;DR

Goldfish is a novel federated unlearning framework that improves efficiency and validity by combining a new loss function, knowledge distillation, early termination, data partitioning, and adaptive mechanisms, validated through extensive experiments.

Contribution

It introduces a comprehensive federated unlearning framework with innovative modules and techniques to enhance efficiency, validity, and robustness over existing methods.

Findings

Significant reduction in unlearning time compared to baseline methods.

Improved validity and robustness of the unlearned models.

Effective handling of data heterogeneity and model quality variance.

Abstract

With recent legislation on the right to be forgotten, machine unlearning has emerged as a crucial research area. It facilitates the removal of a user's data from federated trained machine learning models without the necessity for retraining from scratch. However, current machine unlearning algorithms are confronted with challenges of efficiency and validity. To address the above issues, we propose a new framework, named Goldfish. It comprises four modules: basic model, loss function, optimization, and extension. To address the challenge of low validity in existing machine unlearning algorithms, we propose a novel loss function. It takes into account the loss arising from the discrepancy between predictions and actual labels in the remaining dataset. Simultaneously, it takes into consideration the bias of predicted results on the removed dataset. Moreover, it accounts for the confidence level of predicted results. Additionally, to enhance efficiency, we adopt knowledge a distillation technique in the basic model and introduce an optimization module that encompasses the early termination mechanism guided by empirical risk and the data partition mechanism. Furthermore, to bolster the robustness of the aggregated model, we propose an extension module that incorporates a mechanism using adaptive distillation temperature to address the heterogeneity of user local data and a mechanism using adaptive weight to handle the variety in the quality of uploaded models. Finally, we conduct comprehensive experiments to illustrate the effectiveness of proposed approach.