Apprentissage fédéré interentreprises - Historique des versions

Pitpitt le 24 février 2024 à 23:15

2024-02-24T23:15:38Z

← Version précédente		Version du 24 février 2024 à 19:15
Ligne 18 :		Ligne 18 :
	[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]		[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]

	[[Catégorie:~~Publication~~]]		[[Catégorie:GRAND LEXIQUE FRANÇAIS]]

Pitpitt : Remplacement de texte : « ↵↵↵ » par «   »

2024-01-29T15:24:15Z

Remplacement de texte : « ↵↵↵ » par «   »

← Version précédente		Version du 29 janvier 2024 à 11:24
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 ]

Pitpitt : Remplacement de texte : « ↵↵ » par « ==Sources== »

2024-01-27T20:53:54Z

Remplacement de texte : « ↵↵<small> » par « ==Sources== »

← Version précédente		Version du 27 janvier 2024 à 16:53
Ligne 13 :		Ligne 13 :
	''' cross-silo federated learning'''		''' cross-silo federated learning'''

	<!-- 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->		<!-- 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==

	~~<small>~~

Patrickdrouin : Patrickdrouin a déplacé la page Cross-Silo Federated Learning vers Apprentissage fédéré interentreprises

2023-04-18T19:05:33Z

Patrickdrouin a déplacé la page Cross-Silo Federated Learning vers Apprentissage fédéré interentreprises

← Version précédente	Version du 18 avril 2023 à 15:05
(Aucune différence)

Patrickdrouin le 18 avril 2023 à 19:05

2023-04-18T19:05:18Z

← Version précédente		Version du 18 avril 2023 à 15:05
Ligne 20 :		Ligne 20 :
	[https://arxiv.org/abs/2206.12949 Source : arxiv ]		[https://arxiv.org/abs/2206.12949 Source : arxiv ]
	[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]		[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]

			[[Catégorie:Publication]]

Patrickdrouin le 18 avril 2023 à 19:03

2023-04-18T19:03:40Z

← Version précédente		Version du 18 avril 2023 à 15:03
Ligne 11 :		Ligne 11 :

	== Anglais ==		== Anglais ==
	''' ~~Cross~~-~~Silo Federated Learning~~'''		''' cross-silo federated learning'''

	<!-- 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->		<!-- 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->

Patrickdrouin le 18 avril 2023 à 19:01

2023-04-18T19:01:46Z

← Version précédente		Version du 18 avril 2023 à 15:01
Ligne 7 :		Ligne 7 :
	== Français ==		== Français ==
	''' apprentissage fédéré interentreprises '''		''' apprentissage fédéré interentreprises '''
	'' apprentissage fédéré interdépartemental '''
			''' apprentissage fédéré interdépartemental '''

	== Anglais ==		== Anglais ==

Patrickdrouin le 18 avril 2023 à 19:01

2023-04-18T19:01:08Z

← Version précédente		Version du 18 avril 2023 à 15:01
Ligne 12 :		Ligne 12 :
	''' Cross-Silo Federated Learning'''		''' Cross-Silo Federated Learning'''

	<!- 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->		<!-- 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->

	<small>		<small>

Patrickdrouin le 18 avril 2023 à 18:56

2023-04-18T18:56:08Z

← Version précédente		Version du 18 avril 2023 à 14:56
Ligne 19 :		Ligne 19 :
	[https://arxiv.org/abs/2206.12949 Source : arxiv ]		[https://arxiv.org/abs/2206.12949 Source : arxiv ]
	[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]		[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]

	~~[[Catégorie:vocabulary]]~~

Patrickdrouin le 18 avril 2023 à 18:55

2023-04-18T18:55:44Z

← Version précédente		Version du 18 avril 2023 à 14:55
Ligne 1 :		Ligne 1 :
	==~~en construction~~==		== 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).

	== ~~Définition~~ ==		==Compléments==
	~~XXXXXXXXX~~		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 ==		== Français ==
	''' ~~XXXXXXXXX~~ '''		''' apprentissage fédéré interentreprises '''
			'' apprentissage fédéré interdépartemental '''

	== Anglais ==		== Anglais ==
	''' Cross-Silo Federated Learning'''		''' Cross-Silo Federated Learning'''

	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		<!- 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->

	<small>		<small>
Ligne 16 :		Ligne 18 :

	[https://arxiv.org/abs/2206.12949 Source : arxiv ]		[https://arxiv.org/abs/2206.12949 Source : arxiv ]
			[https://blog.openmined.org/federated-learning-types/ Source : OpenMined]

	[[Catégorie:vocabulary]]		[[Catégorie:vocabulary]]

Apprentissage fédéré interentreprises - Historique des versions

Pitpitt le 24 février 2024 à 23:15

Pitpitt : Remplacement de texte : « ↵↵↵ » par « »

Pitpitt : Remplacement de texte : « ↵↵ » par « ==Sources== »

Patrickdrouin : Patrickdrouin a déplacé la page Cross-Silo Federated Learning vers Apprentissage fédéré interentreprises

Patrickdrouin le 18 avril 2023 à 19:05

Patrickdrouin le 18 avril 2023 à 19:03

Patrickdrouin le 18 avril 2023 à 19:01

Patrickdrouin le 18 avril 2023 à 19:01

Patrickdrouin le 18 avril 2023 à 18:56

Patrickdrouin le 18 avril 2023 à 18:55

Pitpitt : Remplacement de texte : « ↵↵↵ » par «   »

Pitpitt : Remplacement de texte : « ↵↵ » par « ==Sources== »

Patrickdrouin : Patrickdrouin a déplacé la page Cross-Silo Federated Learning vers Apprentissage fédéré interentreprises