Personalized Federated Learning via Sequential Layer Expansion in Representation Learning

arXiv:2404.17799v1 Announce Type: new
Abstract: Federated learning ensures the privacy of clients by conducting distributed training on individual client devices and sharing only the model weights with a central server. However, in real-world scenarios, the heterogeneity of data among clients necessitates appropriate personalization methods. In this paper, we aim to address this heterogeneity using a form of parameter decoupling known as representation learning. Representation learning divides deep learning models into 'base' and 'head' components. The base component, capturing common features …

abstract aim arxiv client cs.ai cs.lg data devices distributed expansion federated learning however layer paper personalization personalized privacy representation representation learning server training type via world