arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1710.03444stat.MLcs.LG
收藏

和积网络的安全半监督学习

Safe Semi-Supervised Learning of Sum-Product Networks

Graz University of Technology(格拉茨技术大学);Austrian Research Institute for Artificial Intelligence(奥地利人工智能研究所);University of Cambridge(剑桥大学)

Martin Trapp, Tamas Madl, Robert Peharz, Franz Pernkopf, Robert Trappl

摘要:

在一些领域中,获取类注释是昂贵的,而同时未标记的数据是丰富的。虽然大多数半监督方法都对数据分布进行了限制性假设,但最近的工作已经成功地在非限制性机制中学习半监督模型。然而,到目前为止,这样的方法只提出了线性模型。在这项工作中,我们介绍了和积网络(SPN)的半监督参数学习。SPN是深度概率模型,允许在线性时间内推理网络边缘的数量。我们的方法有几个优点,因为它(1)允许生成和判别式半监督学习,(2)保证添加未标记数据可以增加,但不会降低性能(安全),(3)计算效率高,不会对数据分布进行限制性假设。我们在各种数据集上表明,与最先进的方法相比,使用SPN的安全半监督学习具有竞争力,并且可以比纯监督方法产生更好的生成性和区分性客观值。

英文摘要:

In several domains obtaining class annotations is expensive while at the same time unlabelled data are abundant. While most semi-supervised approaches enforce restrictive assumptions on the data distribution, recent work has managed to learn semi-supervised models in a non-restrictive regime. However, so far such approaches have only been proposed for linear models. In this work, we introduce semi-supervised parameter learning for Sum-Product Networks (SPNs). SPNs are deep probabilistic models admitting inference in linear time in number of network edges. Our approach has several advantages, as it (1) allows generative and discriminative semi-supervised learning, (2) guarantees that adding unlabelled data can increase, but not degrade, the performance (safe), and (3) is computationally efficient and does not enforce restrictive assumptions on the data distribution. We show on a variety of data sets that safe semi-supervised learning with SPNs is competitive compared to state-of-the-art and can lead to a better generative and discriminative objective value than a purely supervised approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑