Goldfish: An Efficient Federated Unlearning Framework
Authors:
- 24 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 252-264
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.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- FedRecovery: Differentially Private Machine Unlearning for Federated Learning FrameworksIEEE Transactions on Information Forensics and Security, 2023
- Machine unlearning: linear filtration for logit-based classifiersMachine Learning, 2022
- The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining2022
- FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models2021
- Machine Unlearning2021
- Analyzing User-Level Privacy Attack Against Federated LearningIEEE Journal on Selected Areas in Communications, 2020
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning2019
- Focal Loss for Dense Object Detection2017
- Deep Residual Learning for Image Recognition2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998