Analog and Digital Wireless Communications for Computations
You are invited to participate in this joint event of IEEE ComSoc PT Chapter and IEEE VTS PT Chapter, held at INSTITUTO DE TELECOMUNICAÇÕES, Pólo de Aveiro, Universidade de Aveiro, Aveiro, Portugal.
In recent years, the demand for machine learning (ML) services over wireless networks has driven the development of new communication protocols to support these services efficiently. ML services on wireless networks face challenges in computation, bandwidth, scalability, privacy, and security. One approach to address these issues is Over-the-air computation (OAC), a technique where wireless devices transmit values via analog amplitude modulation. This allows a function of these values (e.g., Federated Learning gradient aggregation) to be computed at a common receiver through the communication channel itself. OAC significantly reduces communication energy use, enhances spectrum efficiency by orders of magnitude, and strengthens privacy protections. This is achieved by leveraging the superposition properties of electromagnetic waves, which naturally sum analog values. As a result, OAC is mostly applied in analog communication systems. However, using digital communication for OAC could offer advantages like error correction, synchronization, channel state information acquisition, and easier integration with current digital communication systems. In this talk, we introduce ChannelComp, a new method enabling OAC through digital modulation. We demonstrate that digital modulation allows for a broader class of computable functions compared to traditional OAC and propose an optimization problem to identify the optimal digital modulation for over-the-air computation. Simulation results highlight ChannelComp’s superior performance over OAC.
Date and Time
Location
Hosts
Registration
- Date: 14 Nov 2024
- Time: 09:30 AM to 11:00 AM
- All times are (UTC+00:00) Lisbon
-
Add Event to Calendar
- Instituto de Telecomunicações
- Campus Universitário de Santiago
- Aveiro, Centro
- Portugal 3810-1
- Building: Instituto de Telecomunicações (Edificio 19 da Universidade de Aveiro)
- Room Number: Anfiteatro
- Click here for Map
- Contact Event Hosts
- Co-sponsored by INSTITUTO DE TELECOMUNICAÇÕES
- Starts 01 November 2024 12:00 AM
- Ends 15 November 2024 12:00 AM
- All times are (UTC+00:00) Lisbon
- No Admission Charge
- Menu: IEEE Member, Non-IEEE Member
Speakers
Carlo Fischione of KTH Royal Institute of Technology
Analog and Digital Wireless Communications for Computations
A joint event of the IEEE ComSoc PT Chapter and IEEE VTS PT Chapter.
Biography:
Dr. Carlo Fischione is full Professor at KTH Royal Institute of Technology, Electrical Engineering and Computer Science, Division of Network and Systems Engineering (NSE), Stockholm, Sweden. He is Director of the KTH-Ericsson Data Science Micro Degree Program directed to Ericsson globally, Director of the undergraduate education at NSE, Chair of the IEEE Machine Learning for Communications Emerging Technologies Initiative, and founding General Chair of the IEEE International Conference on Machine Learning for Communications and Networking – IEEE ICMLCN 2024. He is distinguished lecturer of the IEEE Communication Society. He received the Ph.D. degree in Electrical and Information Engineering in May 2005. Prof. Fischione has held research positions at Massachusetts Institute of Technology, Cambridge, MA (2015, Visiting Professor); Harvard University, Cambridge, MA (2015, Associate); and University of California at Berkeley, CA (2004-2005, Visiting Scholar, and 2007-2008, Research Associate). He is Honorary Professor at University of L’Aquila, Italy, Department of Mathematics, Information Engineering, and Computer Science. His research interests include applied optimization, wireless Internet of Things, and machine learning. He received a number of awards, such as the "IEEE Communication Society S. O. Rice" award for the best IEEE Transactions on Communications paper of 2018, the best paper award of IEEE Transactions on Industrial Informatics (2007). He is Editor of IEEE Transactions on Communications (Machine Learning for Communications area) and IEEE Transactions on Machine Learning for Communication and Networking, and has served as Associated Editor of IFAC Automatica (2014-2019).
Email:
Address:KTH Royal Institute of Technology, Electrical Engineering and Computer Science, Division of Network and Systems Engineering, TEKNIKRINGEN 33, Stockholm, Sweden, 10044
Agenda
09:30 Carlo Fischione, Analog and Digital Wireless Communications for Computations
Media
| Photo | 601.16 KiB | |
| Photo2 | 494.51 KiB |