1 citations · 1 across the 2 of their papers we have counts for
4 papers
FLAIR: Distributed Federated Learning with Dynamic Clustering
Ihssan Boutebicha, Bilel Zaghdoudi, Mohamed Amine Legheraba +1
Federated Learning (FL) offers a privacy-preserving framework for distributed machine learning, yet conventional centralized and hierarchical architectures present significant chal…
HEAL: Resilient and Self-* Hub-based Learning
Mohamed Amine Legheraba, Stefan Galkiewicz, Maria Gradinariu Potop-Butucaru +1
Decentralized learning enhances privacy, scalability, and fault tolerance by distributing data and computation across nodes. A popular approach is Federated learning, which relies…
Emergent Peer-to-Peer Multi-Hub Topology
Mohamed Amine Legheraba, Maria Potop-Butucaru, Sébastien Tixeuil +1
In this paper we propose and evaluate an innovative algorithm that enables the creation of Peer-to-Peer network overlays characterized by emergent multi-hubs. This approach generat…
LIFT: Byzantine Resilient Hub-Sampling
Mohamed Amine Legheraba, Nour Rachdi, Maria Gradinariu Potop-Butucaru +1
Recently, a novel peer sampling protocol, Elevator, was introduced to construct network topologies tailored for emerging decentralized applications such as federated learning and b…