pFedBBN: 一种针对类别不平衡数据的个性化联邦测试时间适应方法，采用平衡批量归一化
pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data
AI总结：
pFedBBN通过平衡批量归一化实现个性化联邦测试时间适应，解决类别不平衡和分布偏移问题，无需客户端数据。
摘要：
在联邦学习（FL）中，测试时间适应（TTA）对于处理客户端间未见的数据分布至关重要，尤其是在面临领域偏移和类别分布倾斜时。类别不平衡（CI）仍然是FL中的基本挑战，其中罕见但关键的类别往往在个别客户端数据集中严重不足。尽管先前工作通过可靠的聚合和本地类别分布对齐来解决CI问题，但这些方法通常依赖于标记数据或客户端之间的协调，而没有解决在联邦CI约束下，在推理时间对动态领域或分布偏移进行类别无监督适应的问题。揭示了现有最先进的TTA在联邦客户端适应中的失败，我们提出了pFedBBN，一种个性化联邦测试时间适应框架，通过在本地客户端适应过程中使用平衡批量归一化（BBN）来减轻预测偏见，通过平等对待所有类别，同时启用由BBN相似性引导的客户端协作，确保具有相似平衡表示的客户端相互强化，使适应保持与领域特定特征一致。pFedBBN支持完全无监督的本地适应，并引入了一种类别感知的模型聚合策略，使个性化推理无需牺牲隐私。它通过平衡特征归一化和领域感知协作解决分布偏移和类别不平衡问题，而无需任何客户端的标记或原始数据。在多样化的基线模型上进行的广泛实验表明，pFedBBN在状态-of-the-art FL和TTA方法上一致提高了鲁棒性和少数类性能。
英文摘要：
Test-time adaptation (TTA) in federated learning (FL) is crucial for handling unseen data distributions across clients, particularly when faced with domain shifts and skewed class distributions. Class Imbalance (CI) remains a fundamental challenge in FL, where rare but critical classes are often severely underrepresented in individual client datasets. Although prior work has addressed CI during training through reliable aggregation and local class distribution alignment, these methods typically rely on access to labeled data or coordination among clients, and none address class unsupervised adaptation to dynamic domains or distribution shifts at inference time under federated CI constraints. Revealing the failure of state-of-the-art TTA in federated client adaptation in CI scenario, we propose pFedBBN,a personalized federated test-time adaptation framework that employs balanced batch normalization (BBN) during local client adaptation to mitigate prediction bias by treating all classes equally, while also enabling client collaboration guided by BBN similarity, ensuring that clients with similar balanced representations reinforce each other and that adaptation remains aligned with domain-specific characteristics. pFedBBN supports fully unsupervised local adaptation and introduces a class-aware model aggregation strategy that enables personalized inference without compromising privacy. It addresses both distribution shifts and class imbalance through balanced feature normalization and domain-aware collaboration, without requiring any labeled or raw data from clients. Extensive experiments across diverse baselines show that pFedBBN consistently enhances robustness and minority-class performance over state-of-the-art FL and TTA methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
