1 code implementation • 23 Mar 2024 • Arash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio, János Kertész, Márton Karsai
Fully decentralised federated learning enables collaborative training of individual machine learning models on distributed devices on a network while keeping the training data localised.
no code implementations • 28 Feb 2024 • Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio, Andrea Passarella, Marco Conti
We highlight the challenges in transferring knowledge from peripheral to central nodes, attributed to a dilution effect during model aggregation.
no code implementations • 7 Dec 2023 • Lorenzo Valerio, Chiara Boldrini, Andrea Passarella, János Kertész, Márton Karsai, Gerardo Iñiguez
Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation.
no code implementations • 4 Oct 2023 • Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio, Andrea Passarella, Marco Conti
Thus, fully decentralized learning can help in this case.
no code implementations • 29 Jul 2023 • Luigi Palmieri, Lorenzo Valerio, Chiara Boldrini, Andrea Passarella
Specifically, we highlight the different roles in this process of more or less connected nodes (hubs and leaves), as well as that of macroscopic network properties (primarily, degree distribution and modularity).
no code implementations • 1 Mar 2022 • Kilian Ollivier, Chiara Boldrini, Andrea Passarella, Marco Conti
In this respect, ring #1 can be seen as the semantic fingerprint of the ego network of words.
no code implementations • 20 Sep 2021 • Chiara Boldrini, Raffaele Bruno, Haitam Laarabi
Car sharing is one the pillars of a smart transportation infrastructure, as it is expected to reduce traffic congestion, parking demands and pollution in our cities.
no code implementations • 19 Sep 2021 • Mustafa Toprak, Chiara Boldrini, Andrea Passarella, Marco Conti
In order to validate this claim, we focus on popular feature-extraction prediction algorithms (both unsupervised and supervised) and we extend them to include social-circles awareness.
no code implementations • 25 Jul 2017 • Chiara Boldrini, Raffaele Bruno, Haitam Laarabi
Car sharing is one the pillars of a smart transportation infrastructure, as it is expected to reduce traffic congestion, parking demands and pollution in our cities.