SplitEE: Early Exit in Deep Neural Networks with Split Computing

TL;DR

SplitEE introduces an innovative method combining early exits and split computing in deep neural networks, optimizing resource use on edge devices with minimal accuracy loss through an online, unsupervised learning algorithm.

Contribution

The paper proposes SplitEE, a novel algorithm that adaptively decides computation depth and exit points in DNNs for resource-constrained environments, working in an online, unsupervised manner.

Findings

Achieves over 50% cost reduction compared to full inference.

Maintains less than 2% accuracy drop with cost savings.

Extensively validated on five datasets.

Abstract

Deep Neural Networks (DNNs) have drawn attention because of their outstanding performance on various tasks. However, deploying full-fledged DNNs in resource-constrained devices (edge, mobile, IoT) is difficult due to their large size. To overcome the issue, various approaches are considered, like offloading part of the computation to the cloud for final inference (split computing) or performing the inference at an intermediary layer without passing through all layers (early exits). In this work, we propose combining both approaches by using early exits in split computing. In our approach, we decide up to what depth of DNNs computation to perform on the device (splitting layer) and whether a sample can exit from this layer or need to be offloaded. The decisions are based on a weighted combination of accuracy, computational, and communication costs. We develop an algorithm named SplitEE to learn an optimal policy. Since pre-trained DNNs are often deployed in new domains where the ground truths may be unavailable and samples arrive in a streaming fashion, SplitEE works in an online and unsupervised setup. We extensively perform experiments on five different datasets. SplitEE achieves a significant cost reduction ($>50\%$) with a slight drop in accuracy ($<2\%$) as compared to the case when all samples are inferred at the final layer. The anonymized source code is available at \url{https://anonymous.4open.science/r/SplitEE_M-B989/README.md}.