Lightweight Unsupervised Federated Learning with Pretrained Vision Language Model

arXiv:2404.11046v1 Announce Type: cross
Abstract: Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates that each client labels their data for training, which can be both time-consuming and resource-intensive, and may even be impractical for edge devices. Moreover, the training and transmission of deep models present challenges to the computation and communication capabilities of the clients. To …

abstract arxiv client collective cs.ai cs.cv cs.lg data federated learning however labels language language model privacy training trains type unsupervised vision vision language model