About this document

Fed PGP by ran17080907 is a document available to read on EtoBox.

The document presents Federated Prompt Learning with CLIP Generalization and low-rank Personalization (FedPGP), a method that balances personalization and generalization in federated learning using Vision-Language models. FedPGP employs low-rank adaptation and a prompt-wise contrastive loss to enhance model performance while addressing data heterogeneity among clients. Extensive experiments demonstrate FedPGP

Author

ran17080907

Language

EN