DeepAdapter: A Collaborative Deep Learning Framework for the Mobile Web Using Context-Aware Network Pruning

Yakun Huang, Xiuquan Qiao, Jian Tang, Pei Ren, Ling Liu, Calton Pu, Junliang Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep learning shows great promise in providing more intelligence to the mobile web, but insufficient infrastructure, heavy models, and intensive computation limit the use of deep learning in mobile web applications. In this paper, we present DeepAdapter, a collaborative framework that ties the mobile web with an edge server and a remote cloud server to allow executing deep learning on the mobile web with lower processing latency, lower mobile energy, and higher system throughput. DeepAdapter provides a context-aware pruning algorithm that incorporates the latency, the network condition and the computing capability of the mobile device to fit the resource constraints of the mobile web better. It also provides a model cache update mechanism improving the model request hit rate for mobile web users. At runtime, it matches an appropriate model with the mobile web user and provides a collaborative mechanism to ensure accuracy. Our results show that DeepAdapter decreases average latency by 1.33x, reduces average mobile energy consumption by 1.4x, and improves system throughput by 2.1x with a considerable accuracy. Its contextaware pruning algorithm also improves inference accuracy by up to 0.3% with a smaller and faster model.

Original languageEnglish (US)
Title of host publicationINFOCOM 2020 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages834-843
Number of pages10
ISBN (Electronic)9781728164120
DOIs
StatePublished - Jul 2020
Event38th IEEE Conference on Computer Communications, INFOCOM 2020 - Toronto, Canada
Duration: Jul 6 2020Jul 9 2020

Publication series

NameProceedings - IEEE INFOCOM
Volume2020-July
ISSN (Print)0743-166X

Conference

Conference38th IEEE Conference on Computer Communications, INFOCOM 2020
CountryCanada
CityToronto
Period7/6/207/9/20

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'DeepAdapter: A Collaborative Deep Learning Framework for the Mobile Web Using Context-Aware Network Pruning'. Together they form a unique fingerprint.

Cite this