News & Events

OULU presented ADROIT6G at IEEE ICMLCN on 5-8 May 2024

Our partner from the University of Oulu, Finland, has participated and presented at the IEEE ICMLCN. The IEEE International Conference on Machine Learning for Communication and Networking (IEEE ICMLCN) brings together researchers from the disciplines of Machine Learning (ML) and Communication and Networking, and aims at promoting fundamental and applied research of ML for designing and analyzing communication systems and networks, for developing communication protocols to support ML services, as well as for advancing distributed ML over communication networks.

Title: Balancing Energy Efficiency and Distributional Robustness in Over-the-Air Federated Learning

Presenter: Mohamed Badi
Venue: KTH Royal institute of technology, Stockholm, Sweden, from 5th to 8th May 2024.

Paper abstract:
The growing number of wireless edge devices has magnified challenges concerning energy, bandwidth, latency, and data heterogeneity. These challenges have become bottlenecks for distributed learning. To address these issues, this paper presents a novel approach that ensures energy efficiency for distributionally robust federated learning (FL) with over air computation (AirComp). In this context, to effectively balance robustness with energy efficiency, we introduce a novel client selection method that integrates two complementary insights: a deterministic one that is designed for energy efficiency, and a probabilistic one designed for distributional robustness. Simulation results underscore the efficacy of the proposed algorithm, revealing its superior performance compared to baselines from both robustness and energy efficiency perspectives, achieving more than 3-fold energy savings compared to the considered baselines.

More info about the conference here