Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

École de technologie supérieure

$32,000.00

Towards Multi-Task Learning-Empowered Intelligent Communications

EF 2024-25

Résumé
With fifth generation (5G) communications roll out on its way, the research community has shifted towards the design of the sixth generation (6G). Although we are quite at an early stage, where visions/speculations can be conflicting, there is a general consensus that next generation communications will be established on ubiquitous artificial intelligence (AI) in heterogeneous, and highly distributed and dense networks. This will require research efforts to shift from traditional AI solutions that target specific tasks in isolation, to a more general AI approach that is omnipresent in the system. This research program aims to take a first step towards this objective through a multi-task learning (MTL) approach. In fact, communication systems contain a series of intertwined processing tasks; therefore, the methodology proposed is centered around the idea of simultaneously learning related tasks, which is essential for increasing learning performance and efficiency. The overall objective of this program is to develop a MTL framework for physical (PHY) and medium access control (MAC) layer functions in wireless communications, where data driven solutions for different processing tasks seamlessly coexist in the transmission/reception chain. To this end, the short-term objectives defined in this program are: OBJ1- Since data is essential for the development and testing of any machine learning (ML) solution, the first objective is to develop MTL-suited PHY and MAC layer data generation framework; OBG2- the second objective is to develop MTL approaches for centralized intelligence, i.e. for tasks performed at the management entity (base station, edge, or cloud server); OBJ3- the third objective of this research program is to develop distributed MTL approaches for beyond 5G distributed communication architectures and technologies. The identified short-term objectives are a first step towards our vision to propel MTL as an enabling technology for end-to-end intelligence, where the long-term objective is to coin MTL-based coordinated end-to-end intelligence for both centralized and distributed future generation wireless communication systems. This program will advance knowledge in beyond 5G, and particularly 6G communications, as well as AI. It will contribute to ascertain Canada's research competitiveness in these highly influential technologies. Moreover, the proposed research will also be influential to several other industries that can benefit from the proposed methodology to design data driven solutions for automating/optimizing various centralized or distributed complex systems composed of intertwined tasks.
Programme
Discovery Grants Program - Individual
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2023-04886
Name nom
Selim, Bassant
Department département
Génie des Systèmes
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
32000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1510
Committee name en
Electrical and Computer Engineering
Committee name fr
Génie électrique et informatique
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
Génie électrique et électronique
Research subject en
Wireless communication systems
Research subject fr
Systèmes de télécommunications sans fil
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Towards Multi-Task Learning-Empowered Intelligent Communications
Keywords
wireless communications; beyond 5g; machine learning for communications; radio access networks; integrated terrestrial and non-terrestrial networks; 6g
Application summary
With fifth generation (5G) communications roll out on its way, the research community has shifted towards the design of the sixth generation (6G). Although we are quite at an early stage, where visions/speculations can be conflicting, there is a general consensus that next generation communications will be established on ubiquitous artificial intelligence (AI) in heterogeneous, and highly distributed and dense networks. This will require research efforts to shift from traditional AI solutions that target specific tasks in isolation, to a more general AI approach that is omnipresent in the system. This research program aims to take a first step towards this objective through a multi-task learning (MTL) approach. In fact, communication systems contain a series of intertwined processing tasks; therefore, the methodology proposed is centered around the idea of simultaneously learning related tasks, which is essential for increasing learning performance and efficiency. The overall objective of this program is to develop a MTL framework for physical (PHY) and medium access control (MAC) layer functions in wireless communications, where data driven solutions for different processing tasks seamlessly coexist in the transmission/reception chain. To this end, the short-term objectives defined in this program are: OBJ1- Since data is essential for the development and testing of any machine learning (ML) solution, the first objective is to develop MTL-suited PHY and MAC layer data generation framework; OBG2- the second objective is to develop MTL approaches for centralized intelligence, i.e. for tasks performed at the management entity (base station, edge, or cloud server); OBJ3- the third objective of this research program is to develop distributed MTL approaches for beyond 5G distributed communication architectures and technologies. The identified short-term objectives are a first step towards our vision to propel MTL as an enabling technology for end-to-end intelligence, where the long-term objective is to coin MTL-based coordinated end-to-end intelligence for both centralized and distributed future generation wireless communication systems. This program will advance knowledge in beyond 5G, and particularly 6G communications, as well as AI. It will contribute to ascertain Canada's research competitiveness in these highly influential technologies. Moreover, the proposed research will also be influential to several other industries that can benefit from the proposed methodology to design data driven solutions for automating/optimizing various centralized or distributed complex systems composed of intertwined tasks.