Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
This addresses the challenge of efficient deep learning inference on resource-constrained mobile devices with limited wireless bandwidth, offering an incremental improvement over existing cooperative inference methods.
The paper tackles the problem of high transmission latency in device-edge cooperative inference for deep neural networks by proposing a 2-step pruning framework, achieving up to 25.6x reduction in transmission workload, 6.01x acceleration in computation, and 4.81x reduction in end-to-end latency compared to unpruned partitioning.
Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained mobile devices often requires the help from edge servers via computation offloading. However, offloading through a bandwidth-limited wireless link is non-trivial due to the tight interplay between the computation resources on mobile devices and wireless resources. Existing studies have focused on cooperative inference where DNN models are partitioned at different neural network layers, and the two parts are executed at the mobile device and the edge server, respectively. Since the output data size of a DNN layer can be larger than that of the raw data, offloading intermediate data between layers can suffer from high transmission latency under limited wireless bandwidth. In this paper, we propose an efficient and flexible 2-step pruning framework for DNN partition between mobile devices and edge servers. In our framework, the DNN model only needs to be pruned once in the training phase where unimportant convolutional filters are removed iteratively. By limiting the pruning region, our framework can greatly reduce either the wireless transmission workload of the device or the total computation workload. A series of pruned models are generated in the training phase, from which the framework can automatically select to satisfy varying latency and accuracy requirements. Furthermore, coding for the intermediate data is added to provide extra transmission workload reduction. Our experiments show that the proposed framework can achieve up to 25.6$\times$ reduction on transmission workload, 6.01$\times$ acceleration on total computation and 4.81$\times$ reduction on end-to-end latency as compared to partitioning the original DNN model without pruning.