MDLdroid

a ChainSGD-reduce approach to mobile deep learning for personal mobile sensing

Yu Zhang, Tao Gu, Xi Zhang

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

1 Citation (Scopus)

Abstract

Personal mobile sensing is fast permeating our daily lives to enable activity monitoring, healthcare and rehabilitation. Combined with deep learning, these applications have achieved significant success in recent years. Different from conventional cloud-based paradigms, running deep learning on devices offers several advantages including data privacy preservation and low-latency response for both model inference and update. Since data collection is costly in reality, Google's Federated Learning offers not only complete data privacy but also better model robustness based on multiple user data. However, personal mobile sensing applications are mostly user-specific and highly affected by environment. As a result, continuous local changes may seriously affect the performance of a global model generated by Federated Learning. In addition, deploying Federated Learning on a local server, e.g., edge server, may quickly reach the bottleneck due to resource constraint and serious failure by attacks. Towards pushing deep learning on devices, we present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning for personal mobile sensing applications. To address resource limitation, we propose a ChainSGD-reduce approach which includes a novel chain-directed Synchronous Stochastic Gradient Descent algorithm to effectively reduce overhead among multiple devices. We also design an agent-based multi-goal reinforcement learning mechanism to balance resources in a fair and efficient manner. Our evaluations show that our model training on off-the-shelf mobile devices achieves 2x to 3.5x faster than single-device training, and 1.5x faster than the master-slave approach.

Original languageEnglish
Title of host publicationProceedings - 2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
Place of PublicationLos Alamitos, California
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages73-84
Number of pages12
ISBN (Print)9781728154978
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event19th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2020 - Sydney, Australia
Duration: 21 Apr 202024 Apr 2020

Publication series

Namein Proc. of the 19th ACM/IEEE Conference on Information Processing in Sensor Networks (IPSN 2020)
PublisherACM/IEEE

Conference

Conference19th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN 2020
CountryAustralia
CitySydney
Period21/04/2024/04/20

Keywords

  • Distribute computing
  • Mobile deep learning
  • Neural networks
  • Reinforcement learning
  • Resource allocation

Fingerprint Dive into the research topics of 'MDLdroid: a ChainSGD-reduce approach to mobile deep learning for personal mobile sensing'. Together they form a unique fingerprint.

Cite this