Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Онлайнове федеративне навчання× | Трансферне навчання× | |
|---|---|---|
| Галузь | Машинне навчання | Машинне навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2019–2021 | 2010 (formalized); 1990s (early roots) |
| Автор методу≠ | McMahan, B. et al. (FL foundation); extended to online setting by multiple researchers c. 2019–2021 | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) |
| Тип≠ | Distributed sequential learning | Learning paradigm |
| Основоположне джерело≠ | 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). link ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| Інші назви | OFL, federated online learning, streaming federated learning, real-time federated learning | TL, domain adaptation, fine-tuning, pre-trained model adaptation |
| Пов'язані≠ | 5 | 3 |
| Підсумок≠ | 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. | Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond. |
| ScholarGateНабір даних ↗ |
|
|