Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation

2026-04-06

AI Summary

This work addresses the privacy risks in federated learning where models may still retain information about deleted data. To tackle this challenge, the authors propose the first end-to-end federated unlearning framework, which integrates knowledge distillation with an optimization mechanism to efficiently erase memorized data without requiring storage of historical training samples, while preserving high model accuracy. A novel evaluation framework named Skyeye is introduced, embedding the unlearned model as the discriminator within a generative adversarial network (GAN) to visually and quantitatively assess the degree of forgetting through generated samples. Experimental results demonstrate the superiority of the proposed approach in terms of unlearning efficiency, model performance, and evaluability.

Abstract

With the increasing importance of data privacy and security, federated unlearning has emerged as a novel research field dedicated to ensuring that federated learning models no longer retain or leak relevant information once specific data has been deleted. In this paper, to the best of our knowledge, we propose the first complete pipeline for federated unlearning, which includes a federated unlearning approach and an evaluation framework. Our proposed federated unlearning approach ensures high efficiency and model accuracy without the need to store historical data.It effectively leverages the knowledge distillation model alongside various optimization mechanisms. Moreover, we propose a framework named Skyeye to visualize the forgetting capacity of federated unlearning models. It utilizes the federated unlearning model as the classifier integrated into a Generative Adversarial Network (GAN). Afterward, both the classifier and discriminator guide the generator in generating samples. Throughout this process, the generator learns from the classifier's knowledge. The generator then visualizes this knowledge through sample generation. Finally, the model's forgetting capability is evaluated based on the relevance between the deleted data and the generated samples. Comprehensive experiments are conducted to illustrate the effectiveness of the proposed federated unlearning approach and the corresponding evaluation framework.

Problem

• federated unlearning
• data privacy
• model forgetting
• evaluation framework
• forgotten data

Innovation

• federated unlearning
• knowledge distillation
• GAN-based evaluation
• privacy-preserving machine learning
• model forgetting visualization