250 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Côte d'AzurFR9 papers
- Institut national de recherche en sciences et technologies du numériqueFR4 papers
- EURECOMFR3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Communauté d'universités et d'établissements Université Côte d'AzurFR2 papers
- École Nationale de l’Aviation CivileFR2 papers
- Institut de Biologie ValroseFR2 papers
- University College LondonGB2 papers
- Accenture (Ireland)IE1 paper
- ARGO: Apprentissage, graphes et optimisation distribuéeFR1 paper
- Assistance Publique – Hôpitaux de ParisFR1 paper
- Athinoula A. Martinos Center for Biomedical ImagingUS1 paper
4 papers · 1 filter
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Yann Fraboni, Martin Van Waerebeke, Kevin Scaman +3
Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federate…
A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates
Yann Fraboni, Richard Vidal, Laetitia Kameni +1
We propose a novel framework to study asynchronous federated learning optimization with delays in gradient updates. Our theoretical framework extends the standard FedAvg aggregatio…
Joint data imputation and mechanistic modelling for simulating heart-brain interactions in incomplete datasets
Jaume Banus, Maxime Sermesant, Oscar Camara +1
The use of mechanistic models in clinical studies is limited by the lack of multi-modal patients data representing different anatomical and physiological processes. For example, ne…
Free-rider Attacks on Model Aggregation in Federated Learning
Yann Fraboni, Richard Vidal, Marco Lorenzi
Free-rider attacks against federated learning consist in dissimulating participation to the federated learning process with the goal of obtaining the final aggregated model without…