Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing
This addresses the problem of efficient and reliable CNN inference in edge computing environments, offering an incremental improvement over existing methods.
The paper tackles inference acceleration for CNNs in collaborative edge computing by proposing receptive field-based segmentation and fused-layer parallelization, achieving up to 73% speedup for VGG-16 compared to pre-trained models and outperforming MoDNN.
This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing network. To avoid inference accuracy loss in inference task partitioning, we propose receptive field-based segmentation (RFS). To reduce the computation time and communication overhead, we propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers. In this scheme, the collaborative edge servers (ESs) only need to exchange small fraction of the sub-outputs after computing each fused block. In addition, to find the optimal solution of partitioning a CNN model into multiple blocks, we use dynamic programming, named as dynamic programming for fused-layer parallelization (DPFP). The experimental results show that DPFP can accelerate inference of VGG-16 up to 73% compared with the pre-trained model, which outperforms the existing work MoDNN in all tested scenarios. Moreover, we evaluate the service reliability of DPFP under time-variant channel, which shows that DPFP is an effective solution to ensure high service reliability with strict service deadline.