8 papers
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
Arash Badie-Modiri, Chiara Boldrini, Lorenzo Valerio +2
Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, c…
Operating Regimes of Decentralized Learning Under Mobility and Bandwidth Constraints
Samuele Sabella, Chiara Boldrini, Lorenzo Valerio +2
Decentralized learning is a promising paradigm for collaborative training in mobile and pervasive systems, as it avoids a central coordinator and does not require sharing raw data.…
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…
EARL: Energy-Aware Optimization of Liquid State Machines for Pervasive AI
Zain Iqbal, Lorenzo Valerio
Pervasive AI increasingly depends on on-device learning systems that deliver low-latency and energy-efficient computation under strict resource constraints. Liquid State Machines (…
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…
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…