Improving the Accuracy-Latency Trade-off of Edge-Cloud Computation Offloading for Deep Learning Services

Xiaobo Zhao, Minoo Hosseinzadeh, Nathaniel Hudson, Hana Khamfroush, Daniel Enrique Lucani Rötter

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

13 Citations (Scopus)

Abstract

Offloading tasks to the edge or the Cloud has the potential to improve accuracy of classification and detection tasks as more powerful hardware and machine learning models can be used. The downside is the added delay introduced for sending the data to the Edge/Cloud. In delay-sensitive applications, it is usually necessary to strike a balance between accuracy and latency. However, the state of the art typically considers offloading all-or-nothing decisions, e.g., process locally or send all available data to the Edge (Cloud). Our goal is to expand the options in the accuracy-latency trade-off by allowing the source to send a fraction of the total data for processing. We evaluate the performance of image classifiers when faced with images that have been purposely reduced in quality in order to reduce traffic costs. Using three common models (SqueezeNet, GoogleNet, ResNet) and two data sets (Caltech101, ImageNet) we show that the Gompertz function provides a good approximation to determine the accuracy of a model given the fraction of the data of the image that is actually conveyed to the model. We formulate the offloading decision process using this new flexibility and show that a better overall accuracy-latency tradeoff is attained: 58% traffic reduction, 25% latency reduction, as well as 12% accuracy improvement.

Original languageEnglish
Title of host publication2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings
PublisherIEEE
Publication dateDec 2020
Article number367470
ISBN (Electronic)9781728173078
DOIs
Publication statusPublished - Dec 2020
Event2020 IEEE Globecom Workshops, GC Wkshps 2020 - Virtual, Taipei, Taiwan
Duration: 7 Dec 202011 Dec 2020

Conference

Conference2020 IEEE Globecom Workshops, GC Wkshps 2020
Country/TerritoryTaiwan
CityVirtual, Taipei
Period07/12/202011/12/2020
Series2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings

Fingerprint

Dive into the research topics of 'Improving the Accuracy-Latency Trade-off of Edge-Cloud Computation Offloading for Deep Learning Services'. Together they form a unique fingerprint.
  • Scale-loT

    Lucani Rötter, D. E. (Participant)

    01/01/201831/12/2022

    Project: Research

  • Starting Grant

    Lucani Rötter, D. E. (Participant)

    Starting Grant

    01/02/201701/01/2020

    Project: Research

Cite this