9 papers
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.…
Cycles Protocol: A Peer-to-Peer Electronic Clearing System
Ethan Buchman, Paolo Dini, Shoaib Ahmed +2
For centuries, financial institutions have responded to liquidity challenges by forming closed, centralized clearing clubs with strict rules and membership that allow them to colla…
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…
Multi-Object Tracking for Collision Avoidance Using Multiple Cameras in Open RAN Networks
Jordi Serra, Anton Aguilar, Ebrahim Abu-Helalah +2
This paper deals with the multi-object detection and tracking problem, within the scope of open Radio Access Network (RAN), for collision avoidance in vehicular scenarios. To this…