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。
| 鲁棒主动学习× | 少样本学习× | |
|---|---|---|
| 领域 | 机器学习 | 机器学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2006 | 2011–2017 |
| 提出者≠ | Balcan, M.-F.; Beygelzimer, A.; Langford, J. | Lake, B. M.; Vinyals, O.; Finn, C. et al. |
| 类型≠ | Active learning with robustness guarantees | Meta-learning / low-data learning paradigm |
| 开创性文献≠ | Balcan, M.-F., Beygelzimer, A., & Langford, J. (2006). Agnostic active learning. In Proceedings of the 23rd International Conference on Machine Learning (ICML 2006), pp. 65–72. ACM. DOI ↗ | Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗ |
| 别名 | RAL, noise-tolerant active learning, robust query learning, adversarially robust active learning | FSL, low-shot learning, k-shot learning, meta-learning for few examples |
| 相关≠ | 6 | 4 |
| 摘要≠ | Robust Active Learning extends the standard active learning framework to handle noisy labels, adversarial perturbations, and unreliable oracles. Rather than assuming perfect labeling, it incorporates statistical or adversarial robustness guarantees into the query selection process, maintaining sample efficiency while tolerating corruption in the annotation process. | Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited. |
| ScholarGate数据集 ↗ |
|
|