Communication Efficient DNN Partitioning-based Federated Learning

Efficiently running federated learning (FL) on resource-constrained devices is challenging since they are required to train computationally intensive deep neural networks (DNN) independently. DNN partitioning-based FL (DPFL) has been proposed as one mechanism to accelerate training where the layers of a DNN (or computation) are offloaded from the device to an edge server. However, this creates significant communication overheads since the activation and gradient need to be transferred between the device and the edge server during training. Current techniques reduce the communication introduced by DNN partitioning using local loss-based methods. We demonstrate that these methods adversely impact accuracy and ignore the communication costs incurred when transmitting the activation from the device to the server. This paper proposes ActionFed - a communication efficient framework for DPFL to accelerate training on resource-constrained devices. ActionFed eliminates the transmission of the gradient by developing pre-trained initialization of the DNN model on the device for the first time. This reduces the accuracy degradation seen in local loss-based methods. In addition, ActionFed proposes a novel replay buffer mechanism and implements a quantization-based compression technique to reduce the transmission of the activation. It is experimentally demonstrated that ActionFed can reduce the communication cost by up to 15.77x and accelerates training by up to 3.87x when compared to vanilla DPFL.