Accelerating Split Federated Learning over Wireless Communication Networks
This work addresses the problem of efficient AI deployment on heterogeneous edge devices in wireless networks, representing an incremental advancement by integrating existing techniques for practical optimization.
The paper tackles the challenge of deploying deep neural networks on resource-constrained edge devices by proposing a split federated learning framework that combines federated learning and split learning, optimizing split point selection and bandwidth allocation to minimize system latency, with experiments showing improvements in latency reduction and accuracy.
The development of artificial intelligence (AI) provides opportunities for the promotion of deep neural network (DNN)-based applications. However, the large amount of parameters and computational complexity of DNN makes it difficult to deploy it on edge devices which are resource-constrained. An efficient method to address this challenge is model partition/splitting, in which DNN is divided into two parts which are deployed on device and server respectively for co-training or co-inference. In this paper, we consider a split federated learning (SFL) framework that combines the parallel model training mechanism of federated learning (FL) and the model splitting structure of split learning (SL). We consider a practical scenario of heterogeneous devices with individual split points of DNN. We formulate a joint problem of split point selection and bandwidth allocation to minimize the system latency. By using alternating optimization, we decompose the problem into two sub-problems and solve them optimally. Experiment results demonstrate the superiority of our work in latency reduction and accuracy improvement.