在带有真值标签的大量训练样本的强监督条件下，监督学习技术已经取得了巨大的成功。然而，在真实的任务中，收集监督信息往往代价高昂，因此探索弱监督学习通常是更好的方式。
本文聚焦于三种典型的弱监督学习：不完全、不确切和不准确监督。尽管三者可以分开讨论，但在实际中它们常常同时出现，如图1所示。当然也有针对“混合”情况的相关研究【52，92，93】。此外，还有一些其他类型的弱监督。例如，延时监督也可以视为弱监督，它主要出现在增强学习环境中【94】。由于篇幅限制，本文与其说是一个全面的总结回顾，不如说只是一个文献的索引。对于一些细节感兴趣的读者可以阅读参考文献中的相关文章。值得注意的是，越来越多的研究者开始关注弱监督学习，例如部分监督学习（partially supervised learning），主要关注不完全监督的学习【95】，【96，97】，同时还有一些其他关于弱监督的讨论。
为了便于讨论，本文只关注了二分类问题，而大多数讨论经稍事修改后就可推广至多类问题或回归问题。在多类分类任务中可能出现更复杂的情况【98】。在考虑多标签学习（multi-label learning）【99】时情况可能更为复杂，此时每个样本可能被同时赋予多个标签。用不完全监督举个例子：除了标注示例和未标注示例，多标签任务还会遇到部分标注示例，也就是说一个训练示例只给出了一部分标签【100】。即使只考虑标注数据和未标注数据，这种情况也要比单标签有更多选项，例如在主动学习中，对于选定的未标注示例，既可以询问示例的所有标签【101】，也可以询问某一个特定标签【102】，还可以给一对标签的相关排序【103】。尽管如此，不论是何种数据、何种任务，弱监督学习正在变得越来越重要。
参考文献：
Goodfellow I, Bengio Y and Courville A. Deep Learning. Cambridge: MIT Press, 2016.
Settles B. Active learning literature survey. Technical Re- port 1648. Department of Computer Sciences, University of Wisconsin at Madison, Wisconsin, WI, 2010 [ cs.wisc.edu/∼bsettles/pub/settles.activelearning.pdf].
Chapelle O, Scho ̈lkopf B and Zien A (eds). Semi-Supervised Learning. Cambridge: MIT Press, 2006.
Zhu X. Semi-supervised learning literature survey. Technical Report 1530. Department of Computer Sciences, University of Wisconsin at Madison, Madison, WI, 2008 [ wisc.edu/∼jerryzhu/pub/ssl ̇survey.pdf].
Zhou Z-H and Li M. Semi-supervised learning by disagreement. Knowl Inform Syst 2010; 24: 415–39.
Huang SJ, Jin R and Zhou ZH. Active learning by querying informative and representative examples. IEEE Trans Pattern Anal Mach Intell 2014; 36: 1936–49.
Lewis D and Gale W. A sequential algorithm for training text classi ers. In 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Dublin, Ireland, 1994; 3–12.
Seung H, Opper M and Sompolinsky H. Query by committee. In 5th ACM Workshop on Computational Learning Theory, Pitts- burgh, PA, 1992; 287–94.
Abe N and Mamitsuka H. Query learning strategies using boosting and bagging. In 15th International Conference on Ma- chine Learning, Madison, WI, 1998; 1–9.
Nguyen HT and Smeulders AWM. Active learning using pre- clustering. In 21st International Conference on Machine Learn- ing, Banff, Canada, 2004; 623–30.
Dasgupta S and Hsu D. Hierarchical sampling for active learn- ing. In 25th International Conference on Machine Learning, Helsinki, Finland, 2008; 208–15.
Wang Z and Ye J. Querying discriminative and representative samples for batch mode active learning. In 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, 2013; 158–66.
Dasgupta S, Kalai AT and Monteleoni C. Analysis of perceptron-based active learning. In 28th Conference on Learn- ing Theory, Paris, France, 2005; 249–63.
Dasgupta S. Analysis of a greedy active learning strategy. In Advances in Neural Information Processing Systems 17, Cambridge, MA: MIT Press, 2005; 337–44.
Ka ̈a ̈ria ̈inen M. Active learning in the non-realizable case. In 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Sydney, Australia, 2006; 63–77.
Balcan MF, Broder AZ and Zhang T. Margin based active learn- ing. In 20th Annual Conference on Learning Theory, San Diego, CA, 2007; 35–50.
Hanneke S. Adaptive rates of convergence in active learning. In 22nd Conference on Learning Theory, Montreal, Canada, 2009.
Wang W and Zhou ZH. Multi-view active learning in the non-realizable case. In Advances in Neural Information Processing Systems 23, Cambridge, MA: MIT Press, 2010; 2388–96.