https://scholars.lib.ntu.edu.tw/handle/123456789/632589
標題: | Learning from Label Proportions with Consistency Regularization | 作者: | Tsai, Kuen Han HSUAN-TIEN LIN |
關鍵字: | Consistency Regularization | Learning from Label Proportions | Semi-supervised Learning | Weakly-supervised Learning | 公開日期: | 1-一月-2020 | 卷: | 129 | 來源出版物: | Proceedings of Machine Learning Research | 摘要: | The problem of learning from label proportions (LLP) involves training classifiers with weak labels on bags of instances, rather than strong labels on individual instances. The weak labels only contain the label proportion of each bag. The LLP problem is important for many practical applications that only allow label proportions to be collected because of data privacy or annotation cost, and has recently received lots of research attention. Most existing works focus on extending supervised learning models to solve the LLP problem, but the weak learning nature makes it hard to further improve LLP performance with a supervised angle. In this paper, we take a different angle from semi-supervised learning. In particular, we propose a novel model inspired by consistency regularization, a popular concept in semi-supervised learning that encourages the model to produce a decision boundary that better describes the data manifold. With the introduction of consistency regularization, we further extend our study to non-uniform bag-generation and validation-based parameter-selection procedures that better match practical needs. Experiments not only justify that LLP with consistency regularization achieves superior performance, but also demonstrate the practical usability of the proposed procedures. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/632589 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。