Linganisha mbinu
Pitia mbinu ulizochagua bega kwa bega; safu zinazotofautiana zinaangaziwa.
| Mafunzo yaliyoimarishwa kwa njia ya shirikishi× | Ujifunzaji Nusu-Simamiwa× | |
|---|---|---|
| Nyanja | Ujifunzaji wa Mashine | Ujifunzaji wa Mashine |
| Familia | Machine learning | Machine learning |
| Mwaka wa asili≠ | 2020 | 1970s–2006 (formalized) |
| Mwanzilishi≠ | Li, T. et al. (FedProx); McMahan, B. et al. (FedAvg base) | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Aina≠ | Distributed optimization with regularization | Learning paradigm |
| Chanzo asilia≠ | Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated Optimization in Heterogeneous Networks. Proceedings of Machine Learning and Systems (MLSys), 2, 429–450. link ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Majina mbadala | FedProx, federated learning with regularization, proximal federated learning, penalized federated optimization | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Zinazohusiana≠ | 6 | 5 |
| Muhtasari≠ | Regularized federated learning extends the federated learning framework by adding penalty terms to each client's local objective, anchoring local updates closer to the global model. The canonical formulation — FedProx — adds a proximal term that controls how far any single client can drift, improving convergence and stability when client data distributions differ substantially. | Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained. |
| ScholarGateSeti ya data ↗ |
|
|