Abstract
Federated learning (FL) represents a pivotal shift in machine learning (ML) as it enables collaborative training of local ML models coordinated by a central aggregator, all without the need to exchange local data. However, its application on edge devices is hindered by limited computational capabilities and data communication challenges, compounded by the inherent complexity of Deep Learning (DL) models. Model pruning is identified as a key technique for compressing DL models on devices with limited resources. Nonetheless, conventional pruning techniques typically rely on manually crafted heuristics and demand human expertise to achieve a balance between model size, speed, and accuracy, often resulting in sub-optimal solutions. In this study, we introduce an automated federated learning approach utilizing informed pruning, called AutoFLIP, which dynamically prunes and compresses DL models within both the local clients and the global server. It leverages a federated loss exploration phase to investigate model gradient behavior across diverse datasets and losses, providing insights into parameter significance. Our experiments showcase notable enhancements in scenarios with strong non-IID data, underscoring AutoFLIP's capacity to tackle computational constraints and achieve superior global convergence.
Abstract (translated)
联邦学习（FL）在机器学习（ML）中具有关键性的转变，因为它允许由中央聚合器协调本地ML模型的协同训练，而无需交换本地数据。然而，在边缘设备上应用FL存在计算能力和数据通信挑战的限制，再加上Deep Learning（DL）模型的固有复杂性。模型剪枝被认为是压缩具有有限资源设备的DL模型的关键技术。然而，传统的剪枝技术通常依赖于人工创建的启发式，并需要人类专业知识来达到模型大小、速度和准确性的平衡，往往导致次优解决方案。在本研究中，我们引入了一种自动化的联邦学习方法，利用智能剪枝，称为AutoFLIP，它可以在本地客户端和全局服务器上动态地剪枝和压缩DL模型。它利用联邦损失探索阶段研究了模型梯度行为，提供了对参数重要性的洞察。我们的实验展示了在具有强大非IID数据的情况下显著的增强，突出了AutoFLIP解决计算限制和实现卓越全局收敛的能力。
URL
https://arxiv.org/abs/2405.10271
