« Apprentissage fédéré interentreprises » : différence entre les versions
m (Remplacement de texte : « ↵↵<small> » par « ==Sources== ») |
m (Remplacement de texte : « ↵↵↵ » par « ») |
||
| Ligne 14 : | Ligne 14 : | ||
<!-- Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private. Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL where clients are typically mobile devices and the client number can reach up to a scale of millions; cross-silo FL where clients are organizations or companies and the client number is usually small (e.g., within a hundred). While existing studies mainly focus on cross-device FL, this paper aims to provide an overview of the cross-silo FL. More specifically, we first discuss applications of cross-silo FL and outline its major challenges. We then provide a systematic overview of the existing approaches to the challenges in cross-silo FL by focusing on their connections and differences to cross-device->==Sources== | <!-- Federated learning (FL) is an emerging technology that enables the training of machine learning models from multiple clients while keeping the data distributed and private. Based on the participating clients and the model training scale, federated learning can be classified into two types: cross-device FL where clients are typically mobile devices and the client number can reach up to a scale of millions; cross-silo FL where clients are organizations or companies and the client number is usually small (e.g., within a hundred). While existing studies mainly focus on cross-device FL, this paper aims to provide an overview of the cross-silo FL. More specifically, we first discuss applications of cross-silo FL and outline its major challenges. We then provide a systematic overview of the existing approaches to the challenges in cross-silo FL by focusing on their connections and differences to cross-device->==Sources== | ||
[https://arxiv.org/abs/2206.12949 Source : arxiv ] | [https://arxiv.org/abs/2206.12949 Source : arxiv ] | ||
Version du 29 janvier 2024 à 10:24
Définition
Apprentissage fédéré où les clients sont des organisations ou des entreprises, limitant ainsi le nombre de sources de données (par exemple, moins d'une centaine).
Compléments
La même approche peut être au sein de différents départements d'une même entreprise, ce que les gestionnaires nomment souvent des silos d'après une métaphore calquée de l'anglais.
Français
apprentissage fédéré interentreprises
apprentissage fédéré interdépartemental
Anglais
cross-silo federated learning
Contributeurs: Patrick Drouin, wiki
