Mobiprox: Supporting Dynamic Approximate Computing on Mobiles

Matevz Fabjancic, Octavian Machidon, Hashim Sharif, Yifan Zhao, Sasa Misailovic, Veljko Pejovic

Research output: Contribution to journalArticlepeer-review

Abstract

Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input 'difficulty,' or user needs. The existing compression techniques significantly reduce the memory, processing, and energy tax of DL, yet, the resulting models tend to be permanently impaired, sacrificing the inference power for reduced resource usage. The existing tunable compression approaches, on the other hand, require expensive retraining, do not support arbitrary strategies for adapting the compression and do not provide mobile-ready implementations. In this article, we present Mobiprox, a framework enabling mobile DL with flexible precision. Mobiprox implements tunable approximations of tensor operations and enables runtime-adaptable approximation of individual network layers. A profiler and a tuner included with Mobiprox identify the most promising neural network approximation configurations leading to the desired inference quality with the minimal use of resources. Furthermore, we develop control strategies that depending on contextual factors, such as the input data difficulty, dynamically adjust the approximation levels across a mobile DL model's layers. We implement Mobiprox in Android OS and through experiments in diverse mobile domains, including human activity recognition and spoken keyword detection, demonstrate that it can save up to 15% system-wide energy with a minimal impact on the inference accuracy.

Original languageEnglish (US)
Pages (from-to)16873-16886
Number of pages14
JournalIEEE Internet of Things Journal
Volume11
Issue number9
DOIs
StatePublished - May 1 2024

Keywords

  • Adaptation models
  • approximate computing
  • Computational modeling
  • context-awareness
  • Deep learning
  • Hardware
  • mobile deep learning
  • Quantization (signal)
  • Runtime
  • Tensors
  • ubiquitous computing
  • Approximate computing
  • mobile deep learning (DL)

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Mobiprox: Supporting Dynamic Approximate Computing on Mobiles'. Together they form a unique fingerprint.

Cite this