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。
| 自监督 K-近邻× | 半监督K近邻× | |
|---|---|---|
| 领域 | 机器学习 | 机器学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2018–2020 | 2002 (semi-supervised extension); 1967 (KNN base) |
| 提出者≠ | Wu, Z. et al. / Chen, T. et al. | Zhu, X. & Ghahramani, Z. (label propagation); Cover, T. & Hart, P. (KNN base) |
| 类型≠ | Self-supervised + non-parametric classifier | Semi-supervised classifier / label propagation |
| 开创性文献≠ | Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗ | Zhu, X. & Ghahramani, Z. (2002). Learning from labeled and unlabeled data with label propagation. Technical Report CMU-CALD-02-107, Carnegie Mellon University. link ↗ |
| 别名 | SSL-kNN, self-supervised kNN classifier, kNN evaluation probe, nearest-neighbor self-supervised classifier | SS-KNN, semi-supervised KNN, KNN label propagation, graph-based semi-supervised KNN |
| 相关 | 4 | 4 |
| 摘要≠ | Self-supervised K-nearest neighbors (SSL-kNN) combines representation learning without labels with a non-parametric k-NN classifier. A neural encoder is first trained via a self-supervised objective — such as contrastive or masked prediction — so that semantically similar samples cluster together in the embedding space. A simple k-NN lookup on those embeddings then assigns class labels, serving both as a lightweight probe and as a practical classifier. | Semi-supervised KNN extends the classic K-nearest neighbors algorithm to exploit large pools of unlabeled data alongside a small labeled set. By building a KNN graph over all observations and propagating known labels through the graph's edges, the method infers labels for unlabeled points without requiring expensive manual annotation of every sample. |
| ScholarGate数据集 ↗ |
|
|