no code implementations • 15 Jan 2024 • Nikolaos Koursioumpas, Lina Magoula, Ioannis Stavrakakis, Nancy Alonistioti, M. A. Gutierrez-Estevez, Ramin Khalili
Alternative solutions have been surfaced (e. g. Split Learning, Federated Learning), distributing AI tasks of reduced complexity across nodes, while preserving the privacy of the data.
no code implementations • 21 Aug 2023 • Nikolaos Koursioumpas, Lina Magoula, Nikolaos Petropouleas, Alexandros-Ioannis Thanopoulos, Theodora Panagea, Nancy Alonistioti, M. A. Gutierrez-Estevez, Ramin Khalili
Progressing towards a new era of Artificial Intelligence (AI) - enabled wireless networks, concerns regarding the environmental impact of AI have been raised both in industry and academia.
no code implementations • 25 Jun 2023 • Lina Magoula, Nikolaos Koursioumpas, Alexandros-Ioannis Thanopoulos, Theodora Panagea, Nikolaos Petropouleas, M. A. Gutierrez-Estevez, Ramin Khalili
Federated Learning (FL) has emerged as a decentralized technique, where contrary to traditional centralized approaches, devices perform a model training in a collaborative manner, while preserving data privacy.
no code implementations • 14 Jul 2021 • M. A. Gutierrez-Estevez, Martin Kasparick, Renato L. G. Cavalvante, Sławomir Stańczak
Pure data-driven methods can achieve good performance without assuming any physical model, but their complexity and their lack of robustness is not acceptable for many applications.