arXiv subjects

Mohamed Amine Legheraba

Publications and source records attributed to Mohamed Amine Legheraba.

4 recordsLinked to original sources

arXiv2026

FLAIR: Distributed Federated Learning with Dynamic Clustering

Federated Learning (FL) offers a privacy-preserving framework for distributed machine learning, yet conventional centralized and hierarchical architectures present significant challenges in terms of scalability, resilience, and single points of failure, particularly in dynamic, infrastructure-less environments such as sensor networks. To address these limitations, we introduce FLAIR, a novel, fully decentralized FL protocol that integrates dynamic, resource-aware secure and self-organized clustering with in-cluster model training. FLAIR leverages a probabilistic, verifiable cluster-head election mechanism, which is enhanced to favor nodes with greater computational and communication capabilities, thereby ensuring both fairness and efficiency. Through comprehensive simulations in ns-3, we evaluate FLAIR against centralized, hierarchical, and gossip-based FL benchmarks across four demanding scenarios. The results demonstrate the superiority of our approach: in static 100-node networks, FLAIR achieves a final accuracy of approximately 0.91, outperforming all baselines. The protocol exhibits exceptional robustness, maintaining graceful degradation with accuracy above 0.85 even under 90% node failure rates. Furthermore, it shows strong resilience to mobility, with a performance loss of less than 2% compared to static deployments. In a realistic smart farming simulation, FLAIR's accuracy is within 0.2% of the centralized baseline, confirming its practical viability. These findings validate that FLAIR successfully combines the scalability of decentralized learning with the structural efficiency of clustering, presenting a robust and high performing solution for large-scale, heterogeneous IoT systems.

cs.NI↗

arXiv2026

HEAL: Resilient and Self-* Hub-based Learning

Decentralized learning enhances privacy, scalability, and fault tolerance by distributing data and computation across nodes. A popular approach is Federated learning, which relies on a central aggregator, yet faces challenges such as server vulnerabilities, scalability issues, privacy risks and most importantly, the single point of failure. Alternatively Gossip Learning and Epidemic Learning offer fully decentralization through peer-to-peer exchanges of model updates, ensuring robustness and privacy, at the price of slower model convergence. In this work, we introduce a novel decentralized learning framework called HEAL. HEAL is the first cross-layer decentralized learning framework that exploits an optimized self-organizing and self-healing underlying P2P overlay combining the strengths of Federated Learning, Gossip and Epidemic Learning. Leveraging the recently proposed Elevator algorithm, HEAL promotes dynamically chosen nodes to act as aggregators. Through simulations, we demonstrate that HEAL has similar performances to that of Federated Learning in crash-free settings, while being fully decentralized and fault-tolerant. In crash and churn prone environments HEAL outperforms Gossip and Epidemic Learning.

cs.LG↗

arXiv2026

Emergent Peer-to-Peer Multi-Hub Topology

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 generates overlays that balance between the randomness of a graph and the structure of a star network, resulting in networks that not only feature prominent hubs but also exhibit strong resilience to failures. By leveraging principles of preferential attachment and random attachment, our method allows hubs to form spontaneously, offering a decentralized and fault-tolerant solution ideal for applications requiring both low network diameter and high robustness. The protocol is entirely decentralized, operates asynchronously, and depends exclusively on local information. Nodes organically evolve into hubs and remain indistinguishable from other nodes (except in terms of the number of incoming links). The quantity of hubs that emerge can be predetermined by the application as a network parameter.

cs.DC↗

arXiv2026

LIFT: Byzantine Resilient Hub-Sampling

Recently, a novel peer sampling protocol, Elevator, was introduced to construct network topologies tailored for emerging decentralized applications such as federated learning and blockchain. Elevator builds hub-based topologies in a fully decentralized manner, randomly selecting hubs among participating nodes. These hubs, acting as central nodes connected to the entire network, can be leveraged to accelerate message dissemination. Simulation results have shown that Elevator converges rapidly (within 3--4 cycles) and exhibits robustness against crash failures and churn. However, its resilience to Byzantine adversaries has not been investigated. In this work, we provide the first evaluation of Elevator under Byzantine adversaries and show that even a small fraction (2%) of Byzantine nodes is sufficient to subvert the network. As a result, we introduce LIFT, a new protocol that extends Elevator by employing a cryptographically secure pseudo-random number generator (PRNG) for hub selection, thereby mitigating Byzantine manipulation. In contrast, LIFT withstands adversarial infiltration and remains robust with up to 10% Byzantine nodes. These results highlight the necessity of secure randomness in decentralized hub formation and position LIFT as a more reliable building block for Byzantine-resilient decentralized systems.

cs.CR↗