手法を比較

	Federated Learning（連合学習）	知識蒸留	確率的勾配降下法 (SGD)
分野	プライバシー	深層学習	機械学習
系統	Machine learning	Machine learning	Machine learning
提唱年	2017	2015	1951
提唱者	McMahan et al.	Hinton, G., Vinyals, O. & Dean, J.	Robbins, H. & Monro, S.
種類	Distributed privacy-preserving machine learning	Neural network compression (teacher–student)	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.	Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop.	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	Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillation	SGD, online gradient descent, incremental gradient descent, mini-batch gradient descent
関連	3	5	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.	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.	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.