Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning

2025-04-02

AI Summary

In Internet of Drones (IoD) federated learning (FL), data poisoning and model inversion attacks pose serious threats, yet existing federated unlearning (FU) methods struggle to balance unlearning efficacy with model utility. To address this, we propose SoUL, a novel framework featuring selective neuron pruning guided by model interpretability analysis. SoUL precisely identifies and prunes neurons critical to the target forgetting task but minimally contributive to the primary task—enabling efficient FU on resource-constrained edge devices. Experiments demonstrate that SoUL achieves unlearning accuracy comparable to full retraining, with <0.8% accuracy degradation, while reducing communication overhead by 67% and computational latency by 59%. These improvements significantly enhance practicality and deployability of FL in IoD environments.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The Internet of Drones (IoD), where drones collaborate in data collection and analysis, has become essential for applications such as surveillance and environmental monitoring. Federated learning (FL) enables drones to train machine learning models in a decentralized manner while preserving data privacy. However, FL in IoD networks is susceptible to attacks like data poisoning and model inversion. Federated unlearning (FU) mitigates these risks by eliminating adversarial data contributions, preventing their influence on the model. This paper proposes sky of unlearning (SoUL), a federated unlearning framework that efficiently removes the influence of unlearned data while maintaining model performance. A selective pruning algorithm is designed to identify and remove neurons influential in unlearning but minimally impact the overall performance of the model. Simulations demonstrate that SoUL outperforms existing unlearning methods, achieves accuracy comparable to full retraining, and reduces computation and communication overhead, making it a scalable and efficient solution for resource-constrained IoD networks.

Problem

• Efficiently removes adversarial data influence in federated learning
• Maintains model performance while unlearning specific data contributions
• Reduces computation and communication overhead in drone networks

Innovation

• Selective pruning for efficient unlearning
• Maintains model performance post-unlearning
• Reduces computation and communication overhead