Salīdzināt metodes

	Tiešsaistes federatīvā apmācība	Tiešsaistes apguve
Nozare	Mašīnmācīšanās	Mašīnmācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2019–2021	1958–2000s
Autors	McMahan, B. et al. (FL foundation); extended to online setting by multiple researchers c. 2019–2021	Rosenblatt, F.; Littlestone, N.; Shalev-Shwartz, S. (key contributors)
Tips	Distributed sequential learning	Learning paradigm (sequential model update)
Pirmavots	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).	Shalev-Shwartz, S. (2011). Online Learning and Online Convex Optimization. Foundations and Trends in Machine Learning, 4(2), 107–194.
Citi nosaukumi	OFL, federated online learning, streaming federated learning, real-time federated learning	incremental learning, sequential learning, streaming learning, online machine learning
Saistītās	5	6
Kopsavilkums	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.	Online learning is a machine learning paradigm in which a model is updated incrementally as each new data point arrives, rather than being trained once on a fixed dataset. It is essential when data streams continuously, storage is limited, or the underlying distribution shifts over time. Theoretical performance is measured by cumulative regret relative to the best fixed predictor in hindsight.