<ul><li>Federated learning (FL) is a promising paradigm in distributed learning while preserving user privacy.</li><li>The increasing size of models makes it difficult for users with limited resources to participate in FL.</li><li>The authors propose GeFL, a model-agnostic federated learning approach that incorporates a generative model to aggregate global knowledge across users with heterogeneous models.</li><li>Experimental results show improved performance of GeFL compared to baselines, along with a novel framework GeFL-F that addresses privacy and scalability concerns.</li></ul>

GeFL: Model-Agnostic Federated Learning with Generative Models

Discover more