Advertisement

Causal Discovery of Linear Non-Gaussian Acyclic Model with Small Samples

  • Feng Xie
  • Ruichu CaiEmail author
  • Yan Zeng
  • Zhifeng Hao
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11936)

Abstract

Linear non-Gaussian Acyclic Model (LiNGAM) is a well-known model for causal discovery from observational data. Existing estimation methods are usually based on infinite sample theory and often fail to obtain an ideal result in the small samples. However, it is commonplace to encounter non-Gaussian data with small or medium sample sizes in practice. In this paper, we propose a Minimal Set-based LiNGAM algorithm (MiS-LiNGAM) to address the LiNGAM with small samples. MiS-LiNGAM is a two-phase and greedy search algorithm. Specifically, in the first phase, we find the skeleton of the network using the regression-based conditional independence test, which helps us reduce the complexity in finding the minimal LiNGAM set of the second phase. Further, this independence test we applied guarantees the reliability when the number of conditioning variables increases. In the second phase, we give an efficient method to iteratively select the minimal LiNGAM set with the skeleton and learn the causal network. We also present the corresponding theoretical derivation. The experimental results on simulated networks and real networks are presented to demonstrate the efficacy of our method.

Keywords

LiNGAM Non-Gaussian Small samples Causal discovery 

Notes

Acknowledgement

This work was supported in part by the NSFC-Guangdong Joint Fund under Grant U1501254, in part by the Natural Science Foundation of China under Grant 61876043 and Grant 61472089, in part by the Natural Science Foundation of Guangdong under Grant 2014A030306004 and Grant 2014A030308008, in part by the Science and Technology Planning Project of Guangdong under Grant 2013B051000076, Grant 2015B010108006, and Grant 2015B010131015, in part by the Guangdong High-Level Personnel of Special Support Pro- gram under Grant 2015TQ01X140, in part by the Pearl River S&T Nova Program of Guangzhou under Grant 201610010101, and in part by the Science and Technology Planning Project of Guangzhou under Grant 201902010058.

References

  1. 1.
    Spirtes, P., Glymour, C., Scheines, R., Tillman, R.: Automated search for causal relations: theory and practice (2010)Google Scholar
  2. 2.
    Pearl, J.: The seven tools of causal inference, with reflections on machine learning. Commun. ACM 62(3), 54–60 (2019)CrossRefGoogle Scholar
  3. 3.
    Lele, X., et al.: A pooling-lingam algorithm for effective connectivity analysis of fMRI data. Front. Comput. Neurosci. 8, 125 (2014)MathSciNetGoogle Scholar
  4. 4.
    Sanchez-Romero, R., Ramsey, J.D., Zhang, K., Glymour, M.R.K., Huang, B., Glymour, C.: Estimating feedforward and feedback effective connections from fMRI time series: assessments of statistical methods. Netw. Neurosci. 3(2), 274–306 (2019)CrossRefGoogle Scholar
  5. 5.
    Zhang, K., Chan, L.: Minimal nonlinear distortion principle for nonlinear independent component analysis. J. Mach. Learn. Res. 9(Nov), 2455–2487 (2008)MathSciNetzbMATHGoogle Scholar
  6. 6.
    Al-Yahyaee, K.H., Mensi, W., Al-Jarrah, I.M.W., Tiwari, A.K.: Testing for the Granger-causality between returns in the U.S and GIPSI stock markets. Phys. A: Stat. Mech. Appl. 531, 120950 (2019)CrossRefGoogle Scholar
  7. 7.
    Cai, R., Zhang, Z., Hao, Z., Winslett, M.: Understanding social causalities behind human action sequences. IEEE Trans. Neural Netw. Learn. Syst. 28(8), 1801–1813 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Helajärvi, H., Rosenström, T., et al.: Exploring causality between TV viewing and weight change in young and middle-aged adults. The cardiovascular risk in young finns study. PLoS One 9(7), e101860 (2014)CrossRefGoogle Scholar
  9. 9.
    Spirtes, P., Glymour, C.: An algorithm for fast recovery of sparse causal graphs. Soc. Sci. Comput. Rev. 9(1), 62–72 (1991)CrossRefGoogle Scholar
  10. 10.
    Pearl, J., Verma, T.: A theory of inferred causation. In: Proceedings of the Second International Conference on Principles of Knowledge Representation and Reasoning, KR 1991, pp. 441–452 (1991)Google Scholar
  11. 11.
    Shimizu, S., Hoyer, P.O., Hyvärinen, A., Kerminen, A.: A linear non-Gaussian acyclic model for causal discovery. J. Mach. Learn. Res. 7(Oct), 2003–2030 (2006)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Shimizu, S.: LiNGAM: non-Gaussian methods for estimating causal structures. Behaviormetrika 41(1), 65–98 (2014)CrossRefGoogle Scholar
  13. 13.
    Shimizu, S.: Non-gaussian methods for causal structure learning. Prev. Sci. 20, 1–11 (2018)Google Scholar
  14. 14.
    Hoyer, P.O., Hyttinen, A.: Bayesian discovery of linear acyclic causal models. In: Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 240–248. AUAI Press (2009)Google Scholar
  15. 15.
    Shimizu, S., et al.: DirectLiNGAM: a direct method for learning a linear non-Gaussian structural equation model. J. Mach. Learn. Res. 12(Apr), 1225–1248 (2011)MathSciNetzbMATHGoogle Scholar
  16. 16.
    Hyvärinen, A., Smith, S.M.: Pairwise likelihood ratios for estimation of non-Gaussian structural equation models. J. Mach. Learn. Res. 14(Jan), 111–152 (2013)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Kagan, A.M., Rao, C.R., Linnik, Y.V.: Characterization problems in mathematical statistics (1973)Google Scholar
  18. 18.
    Zhang, H., Zhou, S., Zhang, K., Guan, J.: Causal discovery using regression-based conditional independence tests. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)Google Scholar
  19. 19.
    Spirtes, P., Glymour, C.N., Scheines, R.: Causation, Prediction, and Search. MIT Press, Cambridge (2000)zbMATHGoogle Scholar
  20. 20.
    Pearl, J.: Causality: Models, Reasoning and Inference, vol. 29. Springer, Heidelberg (2000)zbMATHGoogle Scholar
  21. 21.
    Sogawa, Y., Shimizu, S., Shimamura, T., HyväRinen, A., Washio, T., Imoto, S.: Estimating exogenous variables in data with more variables than observations. Neural Netw. 24(8), 875–880 (2011)zbMATHCrossRefGoogle Scholar
  22. 22.
    Cai, R., Zhang, Z., Hao, Z.: SADA: a general framework to support robust causation discovery. In: International Conference on Machine Learning, pp. 208–216 (2013)Google Scholar
  23. 23.
    Hyvärinen, A., Zhang, K., Shimizu, S., Hoyer, P.O.: Estimation of a structural vector autoregression model using non-gaussianity. J. Mach. Learn. Res. 11(May), 1709–1731 (2010)MathSciNetzbMATHGoogle Scholar
  24. 24.
    Hoyer, P.O., Shimizu, S., Kerminen, A.J., Palviainen, M.: Estimation of causal effects using linear non-gaussian causal models with hidden variables. Int. J. Approx. Reason. 49(2), 362–378 (2008)MathSciNetzbMATHCrossRefGoogle Scholar
  25. 25.
    Shimizu, S., Bollen, K.: Bayesian estimation of causal direction in acyclic structural equation models with individual-specific confounder variables and non-Gaussian distributions. J. Mach. Learn. Res. 15(1), 2629–2652 (2014)MathSciNetzbMATHGoogle Scholar
  26. 26.
    Loh, P.-L., Bühlmann, P.: High-dimensional learning of linear causal networks via inverse covariance estimation. J. Mach. Learn. Res. 15(1), 3065–3105 (2014)MathSciNetzbMATHGoogle Scholar
  27. 27.
    Cai, R., Xie, F., Chen, W., Hao, Z.: An efficient kurtosis-based causal discovery method for linear non-Gaussian acyclic data. In 2017 IEEE/ACM 25th International Symposium on Quality of Service, pp. 1–6. IEEE (2017)Google Scholar
  28. 28.
    Hoyer, P.O., et al.: Causal discovery of linear acyclic models with arbitrary distributions. In: Proceedings of the Twenty-Fourth Conference on Uncertainty in Artificial Intelligence, pp. 282–289. AUAI Press (2008)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer ScienceGuangdong University of TechnologyGuangzhouChina
  2. 2.School of Mathematics and Big DataFoshan UniversityFoshanChina

Personalised recommendations