BTFL：一种基于贝叶斯的联邦学习内部与外部数据分布测试时泛化方法
BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning
AI总结：
本文提出基于贝叶斯的测试时泛化方法BTFL，通过双头架构和双贝叶斯框架在样本层面平衡个性化与泛化，以应对联邦学习中内部与外部分布测试时的性能下降问题，并在多数据集上以更低时间成本取得更优效果。
摘要：
联邦学习（Federated Learning，FL）使多个客户端能够在保持数据隐私的同时协作开发全局模型。然而，在线联邦学习部署面临分布偏移和不断演变的测试样本带来的挑战。个性化联邦学习（Personalized Federated Learning，PFL）将全局模型适配到各个客户端的数据分布，但在测试期间难以处理分布外（Out-Of-Distribution，OOD）样本，导致性能下降。在现实场景中，在在线测试期间平衡个性化与泛化至关重要，而现有方法主要关注训练阶段的泛化。为了解决测试时的权衡问题，我们引入了一个新场景：联邦学习中的内部与外部分布测试时泛化（Test-time Generalization for Internal and External Distributions in Federated Learning，TGFL），该场景评估模型在内部分布（Internal Distribution，IND）和外部分布（External Distribution，EXD）下的适应性。我们提出BTFL，一种面向TGFL的基于贝叶斯的测试时泛化方法，在测试期间于样本层面平衡泛化与个性化。BTFL采用双头架构存储局部知识和全局知识，通过一个双贝叶斯框架对预测进行插值，该框架同时考虑历史测试数据和当前样本特征，并具有理论保证和更快的速度。我们的实验表明，BTFL在多个数据集和模型上以更少的时间成本取得了更好的性能。源代码已在 https://github.com/ZhouYuCS/BTFL 公开。
英文摘要：
Federated Learning (FL) enables multiple clients to collaboratively develop a global model while maintaining data privacy. However, online FL deployment faces challenges due to distribution shifts and evolving test samples. Personalized Federated Learning (PFL) tailors the global model to individual client distributions, but struggles with Out-Of-Distribution (OOD) samples during testing, leading to performance degradation. In real-world scenarios, balancing personalization and generalization during online testing is crucial and existing methods primarily focus on training-phase generalization. To address the test-time trade-off, we introduce a new scenario: Test-time Generalization for Internal and External Distributions in Federated Learning (TGFL), which evaluates adaptability under Internal Distribution (IND) and External Distribution (EXD). We propose BTFL, a Bayesian-based test-time generalization method for TGFL, which balances generalization and personalization at the sample level during testing. BTFL employs a two-head architecture to store local and global knowledge, interpolating predictions via a dual-Bayesian framework that considers both historical test data and current sample characteristics with theoretical guarantee and faster speed. Our experiments demonstrate that BTFL achieves improved performance across various datasets and models with less time cost. The source codes are made publicly available at https://github.com/ZhouYuCS/BTFL .
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。
