activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

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…

cs.LG2025

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.…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…