通过梯度差建模误差，实现高效自适应联邦学习
AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling
- 用梯度差近似更新误差，避免计算海森矩阵
- 支持大规模多步自适应训练，提升通信效率
- 适合资源受限的分布式学习场景
联邦学习在通信效率与模型精度之间面临重大挑战，核心问题在于如何以低计算成本近似更新误差。本文提出一种轻量级有效方法——梯度差近似（GDA），利用一阶信息估计局部误差趋势，无需计算完整海森矩阵。该方法构成自适应多步联邦学习（AMSFL）框架的核心组件，为大规模多步自适应训练环境提供统一的误差建模策略。
原文摘要 · Abstract (English)
Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, we propose a lightweight yet effective method called Gradient Difference Approximation (GDA), which leverages first-order information to estimate local error trends without computing the full Hessian matrix. The proposed method forms a key component of the Adaptive Multi-Step Federated Learning (AMSFL) framework and provides a unified error modeling strategy for large-scale multi-step adaptive training environments.
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。