Comparer des méthodes

	Apprentissage Fédéré	Confidentialité différentielle	Distillation de connaissances
Domaine	Protection de la vie privée	Protection de la vie privée	Apprentissage profond
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2017	2006	2015
Auteur d'origine	McMahan et al.	Cynthia Dwork	Hinton, G., Vinyals, O. & Dean, J.
Type	Distributed privacy-preserving machine learning	Privacy-preserving randomized mechanism	Neural network compression (teacher–student)
Source fondatrice	McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. Artificial Intelligence and Statistics, 1273–1282.	Dwork, C. (2006). Differential privacy. International Colloquium on Automata, Languages and Programming (ICALP), 1–12.	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.
Alias	Collaborative Learning, Decentralized Learning, FedAvg, Federe Öğrenme	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation
Apparentées	3	3	5
Résumé	Federated Learning is a distributed machine learning paradigm introduced by McMahan et al. in 2017 in which a global model is trained collaboratively across multiple decentralized clients — such as mobile devices or hospital systems — without ever transferring raw data to a central server. Each participant computes model updates locally using its private data; only those updates, not the underlying data, are communicated and aggregated by the server to improve the shared model.	Differential privacy is a mathematical framework for releasing statistical information about a dataset while providing rigorous guarantees that individual records cannot be identified or inferred. Introduced by Cynthia Dwork in 2006, it formalizes privacy as a probabilistic bound: any single individual's presence or absence in the dataset changes the output distribution by at most a multiplicative factor of e^ε, where ε is the privacy budget controlling the privacy–utility tradeoff.	Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.