Scaling-Up Bayesian Network Learning to Thousands of Variables Using Local Learning Techniques
Scaling-Up Bayesian Network Learning to Thousands of Variables Using Local Learning Techniques
复制标题
使用本地学习技术将贝叶斯网络学习扩展到数千个变量
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Laura E. Brown
中科院分区：
文献类型：
--
作者：
I. Tsamardinos;Laura E. Brown
最先进的贝叶斯网络学习算法不能扩展到超过几百个变量;因此，它们远远不能解决生物医学信息学中大型数据集带来的挑战（例如，基因表达、蛋白质组学或文本分类数据）。在本文中，我们提出了一个BN学习算法，称为最大-最小贝叶斯网络学习（MMBN）算法，可以诱导网络与成千上万的变量，或者，可以选择性地重建感兴趣的区域，如果时间不允许完全重建。MMBN基于一种局部算法，该算法返回网络的目标区域，并将这些部分放在一起。在小数据集上，MMBN优于其他最先进的方法。随后，它的可扩展性证明了从数据完全重建贝叶斯网络与10,000个变量使用普通PC硬件。该新算法将贝叶斯网络学习（NP完全问题）的包络推高了大约两个数量级。
State-of-the-art Bayesian Network learning algorithms do not scale to more than a few hundred variables; thus, they fall far short from addressing the challenges posed by the large datasets in biomedical informatics (e.g., gene expression, proteomics, or text-categorization data). In this paper, we present a BN learning algorithm, called the Max-Min Bayesian Network learning (MMBN) algorithm that can induce networks with tens of thousands of variables, or alternatively, can selectively reconstruct regions of interest if time does not permit full reconstruction. MMBN is based on a local algorithm that returns targeted areas of the network and on putting these pieces together. On a small dataset MMBN outperforms other state-of-the-art methods. Subsequently, its scalability is demonstrated by fully reconstructing from data a Bayesian Network with 10,000 variables using ordinary PC hardware. The novel algorithm pushes the envelope of Bayesian Network learning (an NP-complete problem) by about two orders of magnitude.
从基于人口的婴儿出生和死亡记录中发现因果关系的研究。
DOI：
--
发表时间：
1999
期刊：
Proceedings. AMIA Symposium
影响因子：
--
作者：
Mani,S;Cooper,GF
通讯作者：
Cooper,GF