Federated Learning

Atelier aux Transnumériques 2026 : Résilience et confidentialité de l’IA et de l’IA distribuée
Un regard croisé entre les projets IPoP, SSF-ML-DH et REDEEM sur l’IA de confiance.
févr. 3, 2026 2 min. de lecture Events, AI, Cybersecurity
Atelier aux Transnumériques 2026 : Résilience et confidentialité de l’IA et de l’IA distribuée
Adaptive Collaboration for Online Personalized Distributed Learning with Heterogeneous Clients
We study the problem of online personalized decentralized learning with NNN statistically heterogeneous clients collaborating to …
Citation URL
Federated Majorize-Minimization: Beyond Parameter Aggregation
This paper proposes a unified approach for designing stochastic optimization algorithms that robustly scale to the federated learning …
Citation URL
In-Depth Analysis of Low-rank Matrix Factorisation in a Federated Setting
We analyze a distributed algorithm to compute a low-rank matrix factorization on NNN clients, each holding a local dataset …
Citation URL