Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Alliance Grants

University of the Fraser Valley

$24,890.00

Scalable and trustworthy machine learning over the wireless edge networks

FY 2023-24

Summary
Mobile devices, such as smartphones and tablets, have gained immense popularity for social media usage, online shopping, smart banking, reading news articles and other similar pursuits. The enormous amount of data that is being generated from this widespread usage of mobile devices, is highly valuable, as it can provide insights into consumer behaviour, preferences, and patterns. Organizations use this data to improve their marketing and advertising strategies, enhance the user experience, and develop more intelligent products and services. In order to extract insights and harness the value of the generated data, centralized machine learning (ML) is commonly employed through cloud-based services in which an entire raw data is transmitted to the central server. Nevertheless, the unprecedented growing number of smart mobile devices and increasingly stringent government regulations regarding the handling of personal information render centralized ML impracticable. With the goal of harnessing the power of ML over wireless networks, Federated Learning (FL) has recently emerged as a scalable and trustworthy solution. Despite its promise, the limited resources of wireless edge networks and unfavourable fading characteristics of wireless channels hinder the scalability and trustworthiness of FL. Hence, this project aims to initiate collaboration with renowned international academic researchers to accomplish the following two outcomes: (i) Develop new wireless multiple access schemes that not only enhance security of the learning process, but also enable faster convergence for training and more accurate inference while accommodating massive number of heterogeneous edge devices and (ii) Formulate customized performance metrics for FL that will facilitate in optimizing radio resource management. With proposed international collaboration, the project is anticipated to bring a disruptive shift in design paradigm of wireless edge networks, making them more suitable for FL. This project will have the consequential outcome of empowering the technological industry to design scalable digital services that Canadians can use with peace of mind, knowing that their personal information will remain securely stored on their wireless devices.
Program
Alliance Grants
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
581251-2022
Name nom
Waqar, Omer O
Department département
Science, Faculty of
Organization id
28297
Institution établissement
University of the Fraser Valley
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2022
Award amount
24890
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2525
Research subject group en
Electrical and electronic engineering
Research subject group fr
Wireless communication systems
Research subject en
Génie électrique et électronique
Research subject fr
Systèmes de télécommunications sans fil
Application title
Scalable and trustworthy machine learning over the wireless edge networks
Keyword
Analytical optimization; Communication efficient learning; Data privacy; Distributed machine learning; Edge computing; Radio resource management; Wireless networks
Application summary
Mobile devices, such as smartphones and tablets, have gained immense popularity for social media usage, online shopping, smart banking, reading news articles and other similar pursuits. The enormous amount of data that is being generated from this widespread usage of mobile devices, is highly valuable, as it can provide insights into consumer behaviour, preferences, and patterns. Organizations use this data to improve their marketing and advertising strategies, enhance the user experience, and develop more intelligent products and services. In order to extract insights and harness the value of the generated data, centralized machine learning (ML) is commonly employed through cloud-based services in which an entire raw data is transmitted to the central server. Nevertheless, the unprecedented growing number of smart mobile devices and increasingly stringent government regulations regarding the handling of personal information render centralized ML impracticable. With the goal of harnessing the power of ML over wireless networks, Federated Learning (FL) has recently emerged as a scalable and trustworthy solution. Despite its promise, the limited resources of wireless edge networks and unfavourable fading characteristics of wireless channels hinder the scalability and trustworthiness of FL. Hence, this project aims to initiate collaboration with renowned international academic researchers to accomplish the following two outcomes: (i) Develop new wireless multiple access schemes that not only enhance security of the learning process, but also enable faster convergence for training and more accurate inference while accommodating massive number of heterogeneous edge devices and (ii) Formulate customized performance metrics for FL that will facilitate in optimizing radio resource management. With proposed international collaboration, the project is anticipated to bring a disruptive shift in design paradigm of wireless edge networks, making them more suitable for FL. This project will have the consequential outcome of empowering the technological industry to design scalable digital services that Canadians can use with peace of mind, knowing that their personal information will remain securely stored on their wireless devices.
University of the Fraser Valley - $24,890 Grant (2023… | Canada Spends