手法を比較

	オンライン連合学習	確率的勾配降下法 (SGD)
分野	機械学習	機械学習
系統	Machine learning	Machine learning
提唱年	2019–2021	1951
提唱者	McMahan, B. et al. (FL foundation); extended to online setting by multiple researchers c. 2019–2021	Robbins, H. & Monro, S.
種類	Distributed sequential learning	First-order iterative optimization algorithm
原典	Damaskinos, G., Guerraoui, R., Kermarrec, A.-M., Guirguis, A., Riviere, M., & Tempo, R. (2020). FLEET: Flexible and Efficient Federated Learning for Edge AI. Proceedings of Machine Learning and Systems (MLSys).	Robbins, H. & Monro, S. (1951). A Stochastic Approximation Method. The Annals of Mathematical Statistics, 22(3), 400–407.
別名	OFL, federated online learning, streaming federated learning, real-time federated learning	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
関連	5	3
概要	Online Federated Learning (OFL) combines the privacy-preserving, decentralised structure of federated learning with the sequential, sample-by-sample update regime of online learning. Clients — such as mobile devices or edge sensors — receive a global model, update it on newly arriving local data without sharing raw observations, and contribute compressed updates to a central server that aggregates them in near-real-time.	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.