7 papers
DecHW: Heterogeneous Decentralized Federated Learning Exploiting Second-Order Information
Adnan Ahmad, Chiara Boldrini, Lorenzo Valerio +2
Decentralized Federated Learning (DFL) is a serverless collaborative machine learning paradigm where devices collaborate directly with neighbouring devices to exchange model inform…
Sparing User Time with a Socially-Aware Independent Metaverse Avatar
Theofanis P. Raptis, Chiara Boldrini, Marco Conti +1
The Metaverse is redefining digital interactions by merging physical, virtual, and social dimensions, yet its effects on social networking remain largely unexplored. This work exam…
Mind Reading or Misreading? LLMs on the Big Five Personality Test
Francesco Di Cursi, Chiara Boldrini, Marco Conti +1
We evaluate large language models (LLMs) for automatic personality prediction from text under the binary Five Factor Model (BIG5). Five models -- including GPT-4 and lightweight op…
DODO: Causal Structure Learning with Budgeted Interventions
Matteo Gregorini, Chiara Boldrini, Lorenzo Valerio
Artificial Intelligence has achieved remarkable advancements in recent years, yet much of its progress relies on identifying increasingly complex correlations. Enabling causality a…
The Impact of COVID-19 on Twitter Ego Networks: Structure, Sentiment, and Topics
Kamer Cekini, Elisabetta Biondi, Chiara Boldrini +2
Lockdown measures, implemented by governments during the initial phases of the COVID-19 pandemic to reduce physical contact and limit viral spread, imposed significant restrictions…
The Built-In Robustness of Decentralized Federated Averaging to Bad Data
Samuele Sabella, Chiara Boldrini, Lorenzo Valerio +2
Decentralized federated learning (DFL) enables devices to collaboratively train models over complex network topologies without relying on a central controller. In this setting, loc…