FedHe: Heterogeneous Models and Communication-Efficient Federated Learning
This addresses the challenge of varying device capabilities and communication bottlenecks in federated learning, offering a practical improvement for edge computing applications.
The paper tackles the problem of training heterogeneous models and reducing communication overheads in federated learning, achieving better performance than state-of-the-art algorithms in both communication efficiency and model accuracy.
Federated learning (FL) is able to manage edge devices to cooperatively train a model while maintaining the training data local and private. One common assumption in FL is that all edge devices share the same machine learning model in training, for example, identical neural network architecture. However, the computation and store capability of different devices may not be the same. Moreover, reducing communication overheads can improve the training efficiency though it is still a challenging problem in FL. In this paper, we propose a novel FL method, called FedHe, inspired by knowledge distillation, which can train heterogeneous models and support asynchronous training processes with significantly reduced communication overheads. Our analysis and experimental results demonstrate that the performance of our proposed method is better than the state-of-the-art algorithms in terms of communication overheads and model accuracy.