CV

Postdoctoral Researcher

Linköping University, Sweden

Department of Electrical Engineering (ISY), Division for Communication Systems (KS).

PhD in Computer Science

Centre Inria d'Université Côte d'Azur

Advisor: Giovanni Neglia

MSc in Telecommunication Engineering

Politecnico di Bari

Mentor: Luigi Alfredo Grieco

MSc in Computer Engineering, Double Degree

Université Côte d'Azur

Mentors: Arnaud Legout, Chadi Barakat

Erasmus+ KA107

Kazan National Research Technical University

BSc in Computer Engineering

Politecnico di Bari

Mentor: Gennaro Boggia

FedStale: Leveraging Stale Updates in Federated Learning

European Conference on Artificial Intelligence (ECAI)

This paper introduces FedStale, a novel federated learning algorithm that updates the global model in each round through a convex combination of “fresh” updates from participating clients and “stale” updates from non-participating ones.

Client Heterogeneity in Federated Learning Systems

PhD Thesis, Université Côte d'Azur

This thesis focuses on providing a theoretical understanding of federated learning systems under heterogeneous client participation, analyzing the impact of this heterogeneity on the convergence of federated learning algorithms, and proposing practical solutions for a more efficient system and resource usage.

Federated Learning Under Heterogeneous and Correlated Client Availability

IEEE INFOCOM 2023, IEEE/ACM Transactions on Networking

This paper presents the first convergence analysis for a federated learning algorithm under heterogeneous and correlated client availability. Our analysis highlights how correlation adversely affects the algorithm’s convergence rate and how the aggregation strategy can alleviate this effect.