Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics

arXiv:2401.05146v2 Announce Type: replace
Abstract: Federated Learning (FL) enables collaborative training of a Machine Learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy by keeping data stored locally. Instead of centralizing raw data, FL exchanges locally refined model parameters to build a global model incrementally. While FL is more compliant with emerging regulations such as the European General Data Protection Regulation (GDPR), ensuring the right to be forgotten in this context - allowing FL participants …

abstract arxiv build collaborative cs.cr cs.lg data design evaluation evaluation metrics federated learning global guidelines machine machine learning metrics multiple parameters parties preservation privacy raw survey training type unlearning