activity
20232026
most citedRobustness of Decentralised Learning to Nodes and Data Disruption

4 citations · 6 across the 20 of their papers we have counts for

collaborators
Showing 2024Show all

8 papers · 1 filter

cs.SI2024

A Herd of Young Mastodonts: the User-Centered Footprints of Newcomers After Twitter Acquisition

Francesco Di Cursi, Chiara Boldrini, Andrea Passarella +1

The tremendous success of major Online Social Networks (OSNs) platforms has raised increasing concerns about negative phenomena, such as mass control, fake news, and echo chambers.…

cs.SI2024

Social Isolation, Digital Connection: COVID-19's Impact on Twitter Ego Networks

Kamer Cekini, Elisabetta Biondi, Chiara Boldrini +2

One of the most impactful measures to fight the COVID-19 pandemic in its early first years was the lockdown, implemented by governments to reduce physical contact among people and…

cs.SI2024

Applying the Ego Network Model to Cross-Target Stance Detection

Jack Tacchi, Parisa Jamadi Khiabani, Arkaitz Zubiaga +2

Understanding human interactions and social structures is an incredibly important task, especially in such an interconnected world. One task that facilitates this is Stance Detecti…

cs.SI2024

Unveiling Cognitive Constraints in Language Production: Extracting and Validating the Active Ego Network of Words

Kilian Ollivier, Chiara Boldrini, Andrea Passarella +1

The "ego network of words" model captures structural properties in language production associated with cognitive constraints. While previous research focused on the layer-based str…

cs.LG2024★ 4 cited

Robustness of Decentralised Learning to Nodes and Data Disruption

Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio +3

In the vibrant landscape of AI research, decentralised learning is gaining momentum. Decentralised learning allows individual nodes to keep data locally where they are generated an…

cs.LG2024★ 1 cited

Initialisation and Network Effects in Decentralised Federated Learning

Arash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio +2

Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the trai…

cs.LG2024★ 1 cited

Impact of network topology on the performance of Decentralized Federated Learning

Luigi Palmieri, Chiara Boldrini, Lorenzo Valerio +2

Fully decentralized learning is gaining momentum for training AI models at the Internet's edge, addressing infrastructure challenges and privacy concerns. In a decentralized machin…

cs.SI2024

On the Joint Effect of Culture and Discussion Topics on X (Twitter) Signed Ego Networks

Jack Tacchi, Chiara Boldrini, Andrea Passarella +1

Humans are known to structure social relationships according to certain patterns, such as the Ego Network Model (ENM). These patterns result from our innate cognitive limits and ca…