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

TL;DR

AppealNet is an innovative edge/cloud system that efficiently decides whether to process deep learning tasks locally or in the cloud, significantly reducing energy consumption while maintaining high accuracy.

Contribution

It introduces a two-head neural network architecture that predicts inference difficulty, enabling dynamic edge/cloud collaboration for improved efficiency.

Findings

Up to 40% energy savings compared to existing methods

Maintains high accuracy with reduced energy consumption

Effective on multiple image classification datasets

Abstract

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.