混合联邦学习提升低信噪比下的抗噪训练效果
Hybrid Federated Learning for Noise-Robust Training
- 用户端传梯度或软标签，基站动态分配更新权重
- 双自由度优化使低信噪比下测试准确率显著提升
- 适合通信噪声大、隐私要求高的边缘设备场景
联邦学习（FL）和联邦蒸馏（FD）是保护隐私的分布式学习范式，各自在抗噪能力和训练速度间存在权衡。为克服二者缺陷，本文提出一种混合联邦学习（HFL）框架：每个用户设备（UE）可传输梯度或软标签，基站每轮自适应选择FL与FD更新的权重。我们推导了HFL的收敛性，并引入两种自由度利用方法：(i) 基于Jenks优化的自适应用户聚类，(ii) 基于阻尼牛顿法的自适应权重选择。数值结果表明，当两种自由度均被利用时，HFL在低信噪比（SNR）条件下实现了更优的测试准确率。
原文摘要 · Abstract (English)
Federated learning (FL) and federated distillation (FD) are distributed learning paradigms that train UE models with enhanced privacy, each offering different trade-offs between noise robustness and learning speed. To mitigate their respective weaknesses, we propose a hybrid federated learning (HFL) framework in which each user equipment (UE) transmits either gradients or logits, and the base station (BS) selects the per-round weights of FL and FD updates. We derive convergence of HFL framework and introduce two methods to exploit degrees of freedom (DoF) in HFL, which are (i) adaptive UE clustering via Jenks optimization and (ii) adaptive weight selection via a damped Newton method. Numerical results show that HFL achieves superior test accuracy at low SNR when both DoF are exploited.
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。