提出可自动选融合层的联邦学习方法，提升非独立同分布数据下模型性能。
PLayer-FL: A Principled Approach to Personalized Layer-wise Cross-Silo Federated Learning
- 基于层级敏感度指标，自动判断哪些层适合联邦聚合。
- 仅用一个训练轮次即可确定最优分层点，效果优于现有方法。
- 适合数据异构严重的跨客户端联邦学习场景，减少性能下降。
非独立同分布（non-IID）数据下的联邦学习常导致客户端性能低于本地训练基线。部分联邦学习通过仅聚合早期学习通用特征的层来缓解此问题，但现有方法依赖架构特异性、经验性启发式规则。本文首次系统分析了联邦学习中各层级的泛化动态，发现存在从可共享（安全聚合）到任务特定（应保留在本地）的早期转变。基于此，我们提出普适性分层联邦学习（PLayer-FL），通过单次训练轮次高效计算新颖的联邦敏感度指标，自动选择任务适配的最优分层点。该指标受模型剪枝启发，量化每层对聚合的鲁棒性，揭示聚合由有益转为有害的临界位置。实验表明，该指标与多种通用泛化度量高度相关；且在多样架构上，PLayer-FL表现稳定，相较基线更均衡分配收益，并显著减少客户端性能退化。
原文摘要 · Abstract (English)
Federated learning (FL) with non-IID data often degrades client performance below local training baselines. Partial FL addresses this by federating only early layers that learn transferable features, but existing methods rely on ad-hoc, architecture-specific heuristics. We first conduct a systematic analysis of layer-wise generalization dynamics in FL, revealing an early-emerging transition between generalizable (safe-to-federate) and task-specific (should-remain-local) layers. Building on this, we introduce Principled Layer-wise Federated Learning (PLayer-FL), which aims to deliver the benefits of federation more robustly. PLayer-FL computes a novel federation-sensitivity metric efficiently after a single training epoch to choose the optimal split point for a given task. Inspired by model pruning, the metric quantifies each layer's robustness to aggregation and highlights where federation shifts from beneficial to detrimental. We show that this metric correlates strongly with established generalization measures across diverse architectures. Crucially, experiments demonstrate that PLayer-FL achieves consistently competitive performance across a wide range of tasks while distributing gains more equitably and reducing client-side regressions relative to baselines.
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。