← Search

Hongxia Li

2 accepted papers

2024

Global and Local Prompts Cooperation via Optimal Transport for Federated Learning

CVPR 2024poster

Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature recent research attempted to integrate the powerful pretrained models into federated learning frameworks to simultaneously reduce communic…

2024

Harmonizing Generalization and Personalization in Federated Prompt Learning

ICML 2024poster

Federated Prompt Learning (FPL) incorporates large pre-trained Vision-Language models (VLM) into federated learning through prompt tuning. The transferable representations and remarkable generalization capacity of VLM make them highly compatible with the integration of federated learning. Addressing…