Work

Towards practical federated unlearning: A knowledge distillation solution

Year: 2026

Type: article

Abstract: Federated learning(FL) enables collaborative model training without sharing raw data, yet faces a growing challenge: efficiently removing the influence of a specific client’s data to comply with privacy regulations such as the “right to be forgotten.” In this paper, we introduce a novel knowledge distillation-based federated unlearning framework that enables the global model to “forget” a targeted client’s data while preserving overall performance. Our method constructs a fresh student model by distilling knowledge from the original global model, training it only on data from remaining clients, and strategically replaying representative samples to mitigate disaster unlearning. Experiments conducted in MNIST and CIFAR-10 in various non-IID settings demonstrate that the proposed approach not only achieves verifiable unlearning – validated through membership inference attacks – but also reduces communication overhead and maintains high accuracy across sequential tasks. This work provides a practical, efficient, privacy-preserving solution for federated unlearning in dynamic and heterogeneous environments.

Source: Alexandria Engineering Journal

DOI: 10.1016/j.aej.2026.04.008

Authors: Liping Qiao, Xueting Jia, Fanjin Zeng, Xiaojing Cao

Institutions: Hebei Vocational University of Technology and Engineering, Guangdong University Of Finances and Economics

Language: English

Topic: Privacy-Preserving Technologies in Data

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,900

Funders: Science and Technology Planning Project of Guangdong Province, Humanities and Social Science Fund of Ministry of Education of China