手法を比較

	Federated Learning（連合学習）	差分プライバシー	確率的勾配降下法 (SGD)
分野	プライバシー	プライバシー	機械学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2017	2006	1951
提唱者	McMahan et al.	Cynthia Dwork	Robbins, H. & Monro, S.
種類	Distributed privacy-preserving machine learning	Privacy-preserving randomized mechanism	First-order iterative optimization algorithm
原典	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.	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407.
別名	Collaborative Learning, Decentralized Learning, FedAvg, Federe Öğrenme	DP, epsilon-differential privacy, randomized privacy, Diferansiyel Gizlilik	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
関連	3	3	3
概要	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.	Stochastic Gradient Descent (SGD) is a first-order iterative optimization algorithm, rooted in the stochastic approximation framework introduced by Robbins and Monro in 1951, that minimizes an objective function by updating model parameters using the gradient computed on a single randomly selected training example (or a small mini-batch) at each step. It is the core optimization engine behind modern machine learning and deep learning, enabling the training of models on datasets too large to fit in memory.