Label Propagation with Weak Supervision
Label Propagation with Weak Supervision
复制标题
DOI：
10.48550/arxiv.2210.03594
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Rattana Pukdee;Dylan Sam;Maria-Florina Balcan;Pradeep Ravikumar
中科院分区：
文献类型：
--
作者：
Rattana Pukdee;Dylan Sam;Maria-Florina Balcan;Pradeep Ravikumar
半监督学习和弱监督学习是旨在减少当前机器学习应用中对标记数据日益增长的需求的重要范式。在本文中，我们介绍了一种新的分析经典的标签传播算法（LPA）（朱和Ghahramani，2002年），而且利用有用的先验信息，特别是概率假设标签的未标记的数据。我们提供了一个错误的界限，利用当地的几何性质的基础图形和质量的先验信息。我们还提出了一个框架，将多个来源的嘈杂的信息。特别是，我们考虑弱监管的设置，我们的信息来源是弱标签。我们证明了我们的方法在多个基准弱监督分类任务上的能力，对现有的半监督和弱监督方法进行了改进。
Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In this paper, we introduce a novel analysis of the classical label propagation algorithm (LPA) (Zhu&Ghahramani, 2002) that moreover takes advantage of useful prior information, specifically probabilistic hypothesized labels on the unlabeled data. We provide an error bound that exploits both the local geometric properties of the underlying graph and the quality of the prior information. We also propose a framework to incorporate multiple sources of noisy information. In particular, we consider the setting of weak supervision, where our sources of information are weak labelers. We demonstrate the ability of our approach on multiple benchmark weakly supervised classification tasks, showing improvements upon existing semi-supervised and weakly supervised methods.