方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 在线少样本学习× | 半监督学习× | |
|---|---|---|
| 领域 | 机器学习 | 机器学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2019 | 1970s–2006 (formalized) |
| 提出者≠ | Finn, C. et al. (online meta-learning formalization) | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| 类型≠ | Online learning + meta-learning hybrid | Learning paradigm |
| 开创性文献≠ | Finn, C., Rajeswaran, A., Kakade, S., & Levine, S. (2019). Online Meta-Learning. Proceedings of the 36th International Conference on Machine Learning (ICML), PMLR 97, 1920–1930. link ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| 别名 | online meta-learning, streaming few-shot learning, continual few-shot learning, incremental few-shot learning | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| 相关≠ | 4 | 5 |
| 摘要≠ | Online Few-shot Learning combines the streaming update principle of online learning with the data-efficiency goal of few-shot learning, enabling a model to continuously adapt to new tasks or classes from only a handful of labeled examples as data arrives sequentially — without access to the full historical dataset. | 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. |
| ScholarGate数据集 ↗ |
|
|