Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

The intersection of the Foundation Model (FM) and Federated Learning (FL) provides mutual
benefits, presents a unique opportunity to unlock new possibilities in AI research, and …

Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the
robustness challenge under distribution shifts. However, the lack of consistent settings and …

Federated learning (FL) is an effective machine learning paradigm where multiple clients
can train models based on heterogeneous data in a decentralized manner without …

Federated learning has emerged as a promising paradigm for privacy-preserving
collaboration among different parties. Recently, with the popularity of federated learning, an …

Federated Learning (FL) is a way for machines to learn from data that is kept locally, in order
to protect the privacy of clients. This is typically done using local SGD, which helps to …

Abstract Personalized Federated Learning (pFL) has emerged as a promising solution to
tackle data heterogeneity across clients in FL. However existing pFL methods either (1) …

Personalized federated learning algorithms have shown promising results in adapting
models to various distribution shifts. However, most of these methods require labeled data …

Personalized federated learning (pFL) enables collaborative training among multiple clients
to enhance the capability of customized local models. In pFL, clients may have …

When personalized federated learning (FL) meets large foundation models, new challenges
arise from various limitations in resources. In addition to typical limitations such as data …