AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference

This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions. For a given input, AppealNet accurately predicts on-the-fly whether it can be successfully processed by the DL model deployed on the resource-constrained edge device, and if not, appeals to the more powerful DL model deployed at the cloud. This is achieved by employing a two-head neural network architecture that explicitly takes inference difficulty into consideration and optimizes the tradeoff between accuracy and computation/communication cost of the edge/cloud collaborative architecture. Experimental results on several image classification datasets show up to more than 40% energy savings compared to existing techniques without sacrificing accuracy.

I. Introduction

Over the years, internet-of-things (IoTs) have become increasingly intelligent by employing deep neural network (DNN) models for learning-based processing. Due to the stringent resource constraints of such edge devices, the DNN models used in them must be small. To address this problem, various DNN model compression techniques (e.g., weight pruning [1], quantization [2], knowledge distillation [3]) and compact DNN architectures [4] were proposed for edge computing in the literature.