Loosely Coupled Federated Learning Over Generative Models
This addresses the challenge of applying federated learning in complex, heterogeneous scenarios for clients with diverse machine learning models, though it appears incremental as it builds on existing FL frameworks.
The paper tackles the problems of strict model homogeneity and high communication costs in federated learning by proposing Loosely Coupled Federated Learning (LC-FL), which uses generative models as transmission media, enabling heterogeneous models and reducing communication overhead, with experiments on real-world datasets demonstrating its effectiveness.
Federated learning (FL) was proposed to achieve collaborative machine learning among various clients without uploading private data. However, due to model aggregation strategies, existing frameworks require strict model homogeneity, limiting the application in more complicated scenarios. Besides, the communication cost of FL's model and gradient transmission is extremely high. This paper proposes Loosely Coupled Federated Learning (LC-FL), a framework using generative models as transmission media to achieve low communication cost and heterogeneous federated learning. LC-FL can be applied on scenarios where clients possess different kinds of machine learning models. Experiments on real-world datasets covering different multiparty scenarios demonstrate the effectiveness of our proposal.