Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing

TL;DR

This paper introduces a receptive field-based segmentation method and a fused-layer parallelization scheme for distributed CNN inference in edge computing, significantly improving speed and reliability.

Contribution

It proposes a novel segmentation approach and a dynamic programming-based partitioning method to optimize distributed CNN inference in collaborative edge networks.

Findings

DPFP accelerates VGG-16 inference by up to 73%.

DPFP outperforms existing methods like MoDNN.

The scheme ensures high service reliability under variable network conditions.

Abstract

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.