arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.06123cs.LGstat.ML
收藏

数据流先验知识到贝叶斯模型的动态转换

Dynamic transformation of prior knowledge into Bayesian models for data streams

Hanoi University of Science and Technology(河内科技大学);Institute for Chemical Research, Kyoto University(京都大学化学研究所)

Tran Xuan Bach, Nguyen Duc Anh, Ngo Van Linh, Khoat Than

摘要:

我们考虑如何有效地使用先验知识时,学习贝叶斯模型从流媒体环境中的数据来无限和顺序。这个问题在数据爆炸和丰富的外部知识来源(如预训练模型,本体,维基百科等)的时代非常重要。然后,我们提出了一个新的框架,使不同形式的先验知识纳入一个基础贝叶斯模型的数据流。我们的框架包含了一些现有的流行模型的时间序列/动态数据。大量的实验表明,我们的框架优于现有的方法有很大的利润。特别是,我们的框架可以帮助贝叶斯模型在极短的文本上很好地泛化,而其他方法则过拟合。我们的框架的实现可以在https://github.com/bachtranxuan/TPS.git上获得。

英文摘要:

We consider how to effectively use prior knowledge when learning a Bayesian model from streaming environments where the data come infinitely and sequentially. This problem is highly important in the era of data explosion and rich sources of precious external knowledge such as pre-trained models, ontologies, Wikipedia, etc. We show that some existing approaches can forget any knowledge very fast. We then propose a novel framework that enables to incorporate the prior knowledge of different forms into a base Bayesian model for data streams. Our framework subsumes some existing popular models for time-series/dynamic data. Extensive experiments show that our framework outperforms existing methods with a large margin. In particular, our framework can help Bayesian models generalize well on extremely short text while other methods overfit. The implementation of our framework is available at https://github.com/bachtranxuan/TPS.git.

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。

↑