改进联邦学习框架，支持异步更新与个性化学习。
Smoothing ADMM for Non-convex and Non-smooth Hierarchical Federated Learning
- 用平滑ADMM处理非凸非光滑目标，支持多轮异步更新。
- 可灵活使用不同正则化，实现全局一致与个性化学习。
- 在异构数据下收敛更快、精度更高，适合实际部署场景。
本文提出一种分层联邦学习（FL）框架，通过引入平滑技术扩展交替方向乘子法（ADMM），适用于非凸和非光滑目标。与传统分层FL方法不同，该方法支持异步更新及每轮多次迭代，提升对异构数据和系统环境的适应性。此外，框架可在各层灵活采用不同正则化函数，利用各簇的先验信息，并支持可能非光滑的惩罚项。根据学习目标，可选择总变差范数实现层间一致性，或使用非凸惩罚如最小最大凹惩罚（MCP）或平滑折剪绝对偏差（SCAD）实现个性化学习。实验表明，相比传统方法，该方法在收敛速度和准确率上均表现更优，凸显其在多种联邦学习场景下的鲁棒性与通用性。
原文摘要 · Abstract (English)
This paper presents a hierarchical federated learning (FL) framework that extends the alternating direction method of multipliers (ADMM) with smoothing techniques, tailored for non-convex and non-smooth objectives. Unlike traditional hierarchical FL methods, our approach supports asynchronous updates and multiple updates per iteration, enhancing adaptability to heterogeneous data and system settings. Additionally, we introduce a flexible mechanism to leverage diverse regularization functions at each layer, allowing customization to the specific prior information within each cluster and accommodating (possibly) non-smooth penalty objectives. Depending on the learning goal, the framework supports both consensus and personalization: the total variation norm can be used to enforce consensus across layers, while non-convex penalties such as minimax concave penalty (MCP) or smoothly clipped absolute deviation (SCAD) enable personalized learning. Experimental results demonstrate the superior convergence rates and accuracy of our method compared to conventional approaches, underscoring its robustness and versatility for a wide range of FL scenarios.
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。