提出一种高效联邦遗忘框架，可快速清除有害数据影响且保持模型性能。
Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning
- 通过选择性剪枝识别并移除关键神经元，实现精准遗忘。
- 实验显示精度接近全量重训练，计算与通信开销显著降低。
- 适合资源受限的无人机网络等边缘场景使用。
无人机互联网（IoD）中，无人机协同完成数据采集与分析，广泛应用于监控与环境监测。联邦学习（FL）使无人机在不共享原始数据的前提下协同训练模型，保障数据隐私。然而，IoD网络中的联邦学习易受数据投毒和模型反演攻击。联邦遗忘（FU）通过消除恶意数据的影响来缓解这些风险。本文提出天空遗忘（SoUL）框架，通过选择性剪枝算法，精准识别并剔除对遗忘目标有显著影响但对整体性能影响最小的神经元，从而高效清除不良数据贡献。仿真结果表明，SoUL在准确率上接近全量重训练，同时大幅降低计算与通信开销，是适用于资源受限的IoD网络的可扩展、高效率解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。