arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.09020cs.LGcs.AIstat.ML
收藏

噪声数据下贝叶斯网络结构学习算法的大规模经验验证

Large-scale empirical validation of Bayesian Network structure learning algorithms with noisy data

Queen Mary University of London(伦敦玛丽女王大学);The Alan Turing Institute(图灵研究所)

Anthony C. Constantinou, Yang Liu, Kiattikun Chobtham, Zhigao Guo, Neville K. Kitson

摘要:

在过去的几十年里,许多贝叶斯网络(BN)结构学习算法被提出。每个出版物都为该出版物中提出的算法提供了一个经验或理论案例,并且研究结果往往在其关于哪种算法是“最佳”的声明中不一致。部分原因是没有商定的评价方法来确定其有效性。此外,每个算法都基于一组假设,例如完整的数据和因果充分性,并且倾向于使用符合这些假设的数据进行评估,然而这些假设在现实世界中可能是不切实际的。因此,人们普遍认为,综合表现高估了实际表现,尽管这种情况可能会在多大程度上发生仍然是未知的。本文研究了15种结构学习算法的性能。我们提出了一种方法,将算法应用于数据,结合合成噪声,在努力更好地了解结构学习算法的性能时,应用于实际数据。每个算法都经过多个案例研究、样本大小、噪声类型的测试,并采用多个评估标准进行评估。这项工作涉及大约10,000个图表,总结构学习运行时间为7个月。它提供了第一个大规模的经验验证BN结构学习算法在不同的假设下的数据噪声。结果表明,传统的合成性能可能会高估现实世界的性能10%到50%以上。他们还表明,虽然基于分数的学习通常优于基于约束的学习,但更高的拟合分数并不一定意味着更准确的因果图。为了便于与未来的研究进行比较,我们将所有数据,原始结果,图表和BN模型免费在线提供。

英文摘要:

Numerous Bayesian Network (BN) structure learning algorithms have been proposed in the literature over the past few decades. Each publication makes an empirical or theoretical case for the algorithm proposed in that publication and results across studies are often inconsistent in their claims about which algorithm is 'best'. This is partly because there is no agreed evaluation approach to determine their effectiveness. Moreover, each algorithm is based on a set of assumptions, such as complete data and causal sufficiency, and tend to be evaluated with data that conforms to these assumptions, however unrealistic these assumptions may be in the real world. As a result, it is widely accepted that synthetic performance overestimates real performance, although to what degree this may happen remains unknown. This paper investigates the performance of 15 structure learning algorithms. We propose a methodology that applies the algorithms to data that incorporates synthetic noise, in an effort to better understand the performance of structure learning algorithms when applied to real data. Each algorithm is tested over multiple case studies, sample sizes, types of noise, and assessed with multiple evaluation criteria. This work involved approximately 10,000 graphs with a total structure learning runtime of seven months. It provides the first large-scale empirical validation of BN structure learning algorithms under different assumptions of data noise. The results suggest that traditional synthetic performance may overestimate real-world performance by anywhere between 10% and more than 50%. They also show that while score-based learning is generally superior to constraint-based learning, a higher fitting score does not necessarily imply a more accurate causal graph. To facilitate comparisons with future studies, we have made all data, raw results, graphs and BN models freely available online.

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。

↑