More Industry-friendly: Federated Learning with High Efficient Design
This work addresses the efficiency and personalization challenges in federated learning for industry applications, particularly concerning non-IID datasets and communication costs.
This paper proposes a federated learning method that achieves more stable accuracy and better communication efficiency across various data distributions compared to state-of-the-art methods. It aims to make federated learning more practical for industrial applications.
Although many achievements have been made since Google threw out the paradigm of federated learning (FL), there still exists much room for researchers to optimize its efficiency. In this paper, we propose a high efficient FL method equipped with the double head design aiming for personalization optimization over non-IID dataset, and the gradual model sharing design for communication saving. Experimental results show that, our method has more stable accuracy performance and better communication efficient across various data distributions than other state of art methods (SOTAs), makes it more industry-friendly.