ERA

Download the full-sized PDF of CO-OP: Cooperative Machine Learning from Mobile DevicesDownload the full-sized PDF

Analytics

Share

Permanent link (DOI): https://doi.org/10.7939/R32805C45

Download

Export to: EndNote  |  Zotero  |  Mendeley

Communities

This file is in the following communities:

Graduate Studies and Research, Faculty of

Collections

This file is in the following collections:

Theses and Dissertations

CO-OP: Cooperative Machine Learning from Mobile Devices Open Access

Descriptions

Other title
Subject/Keyword
cooperative machine learning
federated machine learning
machine learning
Type of item
Thesis
Degree grantor
University of Alberta
Author or creator
Wang, Yushi
Supervisor and department
Niu, Di (Department of Electrical and Computer Engineering)
Examining committee member and department
Kong, Linglong (Department of Mathematical and Statistical Sciences)
Wang, Xinhua (Department of Electrical and Computer Engineering)
Department
Department of Electrical and Computer Engineering
Specialization
Computer Engineering
Date accepted
2017-09-25T15:33:56Z
Graduation date
2017-11:Fall 2017
Degree
Master of Science
Degree level
Master's
Abstract
Massive amounts of user behavior logs and sensor data are generated on mobile devices, which can help to improve the usability of social media apps and other intelligent apps. However, collecting such personal data may spark privacy and legal concerns. Recently, many efforts in both academia and industry have been devoted to developing distributed machine learning methods and architectures to scale up to a large amount of distributed data. However, most such methods focus on a server cluster or data residing on several datacenters. This work takes one more step toward the more ambitious objective of collectively training machine learning models based on data from mobile devices, yet without collecting such private data centrally. We propose CO-OP, an asynchronous protocol which leverages the computing power of each mobile client to train local models based on small amounts of newly generated training samples, and merges such local models into a global model on the server judiciously, balancing the model accuracy and communication overhead. We implemented a CO-OP Android app and tested it on 60 real clients distributed in different continents. Results suggest that CO-OP can achieve an accuracy of more than 80% on image classification using neural networks based on the MNIST datasets, even when the clients are intermittently available and training data are generated dynamically on the go. Additional simulation results also demonstrate the effectiveness of CO-OP in training Support Vector Machine (SVM) and Logistic Regression models.
Language
English
DOI
doi:10.7939/R32805C45
Rights
This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for the purpose of private, scholarly or scientific research. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.
Citation for previous publication
T. Zhang*, Y. Wang*, C. Li, and D. Niu, “Co-op: Cooperative machine learn- ing from mobile devices ” submitted to INFOCOM 2018. *These two authors contributed equally to this paper.

File Details

Date Uploaded
Date Modified
2017-09-25T21:33:57.226+00:00
Audit Status
Audits have not yet been run on this file.
Characterization
File format: pdf (PDF/A)
Mime type: application/pdf
File size: 502250
Last modified: 2017:11:08 17:06:42-07:00
Filename: Wang_Yushi_201709_MSc.pdf
Original checksum: c4e8622c94655c744b758017c3dd995b
Well formed: true
Valid: true
Page count: 49
Activity of users you follow
User Activity Date