针对联邦学习中数据分布漂移问题，提出自适应学习率机制提升模型稳定性。
Fed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
- 通过预测不确定性和特征漂移估计，动态调整每客户端每时间步的学习率。
- 在图像与文本任务上，相比基线模型准确率提升2.1%~4.3%，收敛更稳定。
- 适合真实场景中存在数据分布变化的联邦学习系统，尤其适用于无标签环境。
在部署后联邦学习中，需在异构客户端上适应非平稳数据流，且无法获取真实标签。主要挑战在于客户端特定、随时间变化的分布漂移下的学习率选择，固定学习率常导致欠拟合或发散。我们提出 Fed-ADE（基于分布漂移估计的联邦适配），一种无监督联邦适配框架，利用轻量级分布动态估计器。具体而言，Fed-ADE 采用不确定性动态估计捕捉预测不确定性的变化，并通过表示动态估计检测协变量层面的特征漂移，二者结合生成每客户端每时间步的自适应学习率。理论分析表明，动态估计可近似底层分布漂移，并提供动态遗憾和收敛保证。在图像与文本基准上，面对多种分布漂移（标签与协变量）的实验显示，性能持续优于强基线。结果表明，感知分布漂移的适配能有效实现现实世界非平稳性下的鲁棒联邦后适配。
原文摘要 · Abstract (English)
Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-specific, time-varying distribution shifts, where fixed learning rates often lead to underfitting or divergence. We propose Fed-ADE (Federated Adaptation with Distribution Shift Estimation), an unsupervised federated adaptation framework that leverages lightweight estimators of distribution dynamics. Specifically, Fed-ADE employs uncertainty dynamics estimation to capture changes in predictive uncertainty and representation dynamics estimation to detect covariate-level feature drift, combining them into a per-client, per-timestep adaptive learning rate. We provide theoretical analyses showing that our dynamics estimation approximates the underlying distribution shift and yields dynamic regret and convergence guarantees. Experiments on image and text benchmarks under diverse distribution shifts (label and covariate) demonstrate consistent improvements over strong baselines. These results highlight that distribution shift-aware adaptation enables effective and robust federated post-adaptation under real-world non-stationarity.
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。