提出客户端剪枝技术CLIP，加速安全联邦学习训练
CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning
- 客户端侧使用不变神经元剪枝+网络感知剪枝
- 在多个数据集上提速13%~34%，精度损失≤2.6%
- 适合资源受限设备参与安全联邦学习的场景
安全联邦学习（FL）在分布式模型训练中保护数据隐私。然而，在异构设备上部署此类框架时，计算或网络能力有限的慢速客户端（stragglers）会导致整体训练速度下降。本文首次提出针对深度神经网络安全聚合的慢速客户端缓解技术。我们提出CLIP，一种客户端侧的不变神经元剪枝技术，结合网络感知剪枝，有效缓解计算与网络瓶颈，实现最小精度损失。在CIFAR10、Shakespeare、FEMNIST等多个数据集上，该方法使安全联邦学习训练速度提升13%至34%，精度变化范围为1.3%提升至2.6%降低。
原文摘要 · Abstract (English)
Secure federated learning (FL) preserves data privacy during distributed model training. However, deploying such frameworks across heterogeneous devices results in performance bottlenecks, due to straggler clients with limited computational or network capabilities, slowing training for all participating clients. This paper introduces the first straggler mitigation technique for secure aggregation with deep neural networks. We propose CLIP, a client-side invariant neuron pruning technique coupled with network-aware pruning, that addresses compute and network bottlenecks due to stragglers during training with minimal accuracy loss. Our technique accelerates secure FL training by 13% to 34% across multiple datasets (CIFAR10, Shakespeare, FEMNIST) with an accuracy impact of between 1.3% improvement to 2.6% reduction.
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。