Max-Margin Based Learning for Discriminative Bayesian Network from Neuroimaging Data

详细信息    查看全文

• 作者：Luping Zhou (20)
  Lei Wang (20)
  Lingqiao Liu (21)
  Philip Ogunbona (20)
  Dinggang Shen (22)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8675
• 期：1
• 页码：321-328
• 全文大小：348 KB
• 参考文献：1. Bressler, S., Menon, V.: Large-scale brain networks in cognition: emerging methods and principles. Trends Cogn. Sci.聽14(6), 227鈥?90 (2010) CrossRef
  2. Huang, S., Li, J., Ye, J., Fleisher, A., Chen, K., Wu, T., Reiman, E.: A sparse structure learning algorithm for gaussian bayesian network identification from high-dimensional data. IEEE TPAMI聽35(6), 1328鈥?342 (2013) CrossRef
  3. Li, X., Coyle, D., Maguire, L., Watson, D., McGinnity, T.: Gray matter concentration and effective connectivity changes in alzheimer鈥檚 disease: A longitudinal structural mri study. Neuroradiology聽53(10), 733鈥?48 (2011) CrossRef
  4. Kim, J., Zhu, W., Chang, L., Bentler, P., Ernst, T.: Unified structural equation modeling approach for the analysis of multisubject, multivariate functional mri data. Human Brain Mapping聽28, 85鈥?3 (2007) CrossRef
  5. Friston, K., Harrison, L., Penney, W.: Dynamic causal modeling. Neuroimage聽19, 1273鈥?302 (2003) CrossRef
  6. Zhou, L., Wang, L., Liu, L., Ogunbona, P., Shen, D.: Discriminative brain effective connectivity analysis for alzheimers disease: A kernel learning approach upon sparse gaussian bayesian network. In: CVPR, pp. 2243鈥?250 (2013)
  7. Pernkopf, F., Bilmes, J.: Efficient heuristics for discriminative structure learning of bayesian network classifiers. J. Mach. Learn. Res.聽11, 2323鈥?360 (2010)
  8. Guo, Y., Wilkinson, D., Schuurmans, D.: Maximum margin bayesian networks. In: UAI, pp. 233鈥?42. AUAI Press (2005)
  
• 作者单位：Luping Zhou (20)
  Lei Wang (20)
  Lingqiao Liu (21)
  Philip Ogunbona (20)
  Dinggang Shen (22)
  
  20. University of Wollongong, Australia
  21. University of Adelaide, Australia
  22. University of North Carolina at Chapel Hill, USA
  
• ISSN：1611-3349

文摘

Recently, neuroimaging data have been increasingly used to study the causal relationship among brain regions for the understanding and diagnosis of brain diseases. Recent work on sparse Gaussian Bayesian network (SGBN) has shown it as an efficient tool to learn large scale directional brain networks from neuroimaging data. In this paper, we propose a learning approach to constructing SGBNs that are both representative and discriminative for groups in comparison. A max-margin criterion built directly upon the SGBN models is proposed to effectively optimize the classification performance of the SGBNs. The proposed method shows significant improvements over the state-of-the-art works in the discriminative power of SGBNs.