8 papers · 1 filter
Degradation of Feature Space in Continual Learning
Chiara Lanza, Roberto Pereira, Marco Miozzo +2
Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions…
Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Fernanda Famá, Roberto Pereira, Charalampos Kalalas +4
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored.…
Self-Supervised Learning at the Edge: The Cost of Labeling
Roberto Pereira, Fernanda Famá, Asal Rangrazi +3
Contrastive learning (CL) has recently emerged as an alternative to traditional supervised machine learning solutions by enabling rich representations from unstructured and unlabel…
Energy-Efficient Federated Learning for AIoT using Clustering Methods
Roberto Pereira, Fernanda Famá, Charalampos Kalalas +1
While substantial research has been devoted to optimizing model performance, convergence rates, and communication efficiency, the energy implications of federated learning (FL) wit…
Energy Minimization for Participatory Federated Learning in IoT Analyzed via Game Theory
Alessandro Buratto, Elia Guerra, Marco Miozzo +2
The Internet of Things requires intelligent decision making in many scenarios. To this end, resources available at the individual nodes for sensing or computing, or both, can be le…
Enhancing 5G O-RAN Communication Efficiency Through AI-Based Latency Forecasting
Raúl Parada, Ebrahim Abu-Helalah, Jordi Serra +2
The increasing complexity and dynamic nature of 5G open radio access networks (O-RAN) pose significant challenges to maintaining low latency, high throughput, and resource efficien…