Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Puss-uzraudzīta federatīvā apmācība× | Pārneses apmācība× | |
|---|---|---|
| Nozare | Mašīnmācīšanās | Mašīnmācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2020 | 2010 (formalized); 1990s (early roots) |
| Autors≠ | Jeong, W. et al. / multiple independent groups | Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing) |
| Tips≠ | Distributed semi-supervised learning framework | Learning paradigm |
| Pirmavots≠ | Jeong, W., Yoon, J., Yang, E., & Hwang, S. J. (2020). Federated Semi-Supervised Learning with Inter-Client Consistency. International Conference on Learning Representations (ICLR 2021). link ↗ | Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. DOI ↗ |
| Citi nosaukumi | SSL-FL, federated semi-supervised learning, FSSL, semi-supervised distributed learning | TL, domain adaptation, fine-tuning, pre-trained model adaptation |
| Saistītās≠ | 6 | 3 |
| Kopsavilkums≠ | Semi-supervised federated learning (SSFL) trains a shared model across many decentralized clients — each holding private data — when only a subset of clients or a subset of local samples carry labels. It combines the privacy-preserving coordination of federated learning with the label-efficiency of semi-supervised techniques such as pseudo-labeling and consistency regularization, enabling strong model quality without centralizing sensitive data. | 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. |
| ScholarGateDatu kopa ↗ |
|
|