Granger Causality for Heterogeneous Processes

  • Sahar BehzadiEmail author
  • Kateřina Hlaváčková-Schindler
  • Claudia Plant
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


Discovery of temporal structures and finding causal interactions among time series have recently attracted attention of the data mining community. Among various causal notions graphical Granger causality is well-known due to its intuitive interpretation and computational simplicity. Most of the current graphical approaches are designed for homogeneous datasets i.e. the interacting processes are assumed to have the same data distribution. Since many applications generate heterogeneous time series, the question arises how to leverage graphical Granger models to detect temporal causal dependencies among them. Profiting from the generalized linear models, we propose an efficient Heterogeneous Graphical Granger Model (HGGM) for detecting causal relation among time series having a distribution from the exponential family which includes a wider common distributions e.g. Poisson, gamma. To guarantee the consistency of our algorithm we employ adaptive Lasso as a variable selection method. Extensive experiments on synthetic and real data confirm the effectiveness and efficiency of HGGM.

Supplementary material (2.4 mb)
Supplementary material 1 (zip 2414 KB)


  1. 1.
    Arnold, A., Liu, Y., Abe, N.: Temporal causal modelling with graphical Granger methods. In: KDD (2007)Google Scholar
  2. 2.
    Bacsó, N.: Das Klima des Donauraumes. Geoforum (1971)Google Scholar
  3. 3.
    Bahadori, M.T., Liu, Y.: Granger causality analysis in irregular time series. In: SDM (2012)Google Scholar
  4. 4.
    Budhathoki, K., Vreeken, J.: Causal inference by compression. In: ICDM (2016)Google Scholar
  5. 5.
    Budhathoki, K., Vreeken, J.: MDL for causal inference on discrete data. In: ICDM (2017)Google Scholar
  6. 6.
    Budhathoki, K., Vreeken, J.: Causal inference on event sequences. In: SDM (2018)Google Scholar
  7. 7.
    Cheng, D., Bahadori, M.T., Liu, Y.: FBLG: a simple and effective approach for temporal dependence discovery from time series data. In: KDD (2014)Google Scholar
  8. 8.
    Granger, C.W.: Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 424–438 (1969)Google Scholar
  9. 9.
    Kim, S., Putrino, D., Ghosh, S., Brown, E.: A Granger causality measure for point process models of ensemble neural spiking activity. PLOS Comput. Biol. 7, 1–13 (2011)MathSciNetGoogle Scholar
  10. 10.
    Marx, A., Vreeken, J.: Causal inference on multivariate and mixed-type data. In: Berlingerio, M., Bonchi, F., Gärtner, T., Hurley, N., Ifrim, G. (eds.) ECML PKDD 2018. LNCS, vol. 11052, pp. 655–671. Springer, Cham (2019). Scholar
  11. 11.
    McIlhagga, W.: penalized: a MATLAB toolbox for fitting generalized linear models with penalties. J. Stat. Softw. (2016). ArticlesGoogle Scholar
  12. 12.
    Mooij, J.M., Peters, J., Janzing, D., Zscheischler, J., Schölkopf, B.: Distinguishing cause from effect using observational data: methods and benchmarks. J. Mach. Learn. Res. 17, 1103–1204 (2016)MathSciNetzbMATHGoogle Scholar
  13. 13.
    Nelder, J.A., Baker, R.J.: Generalized linear models. In: Encyclopedia of Statistical Sciences (1972)Google Scholar
  14. 14.
    Peters, J., Janzing, D., Schölkopf, B.: Causal inference on discrete data using additive noise models. IEEE Trans. Pattern Anal. Mach. Intell. 33, 2436–2450 (2011)CrossRefGoogle Scholar
  15. 15.
    Qiu, H., Liu, Y., Subrahmanya, N.A., Li, W.: Granger causality for time-series anomaly detection. In: ICDM (2012)Google Scholar
  16. 16.
    Schreiber, T.: Measuring information transfer. Phys. Rev. Lett. 85(2), 461 (2000)CrossRefGoogle Scholar
  17. 17.
    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
  18. 18.
    Shojaie, A., Michailidis, G.: Discovering graphical Granger causality using the truncating lasso penalty. Bioinformatics 26, i517–i523 (2010)CrossRefGoogle Scholar
  19. 19.
    Tibshirani, R.: Regression shrinkage and selection via the Lasso. J. Roy. Stat. Soc. Ser. B (Methodol.) 58, 267–288 (1996)MathSciNetzbMATHGoogle Scholar
  20. 20.
    Zou, H.: The adaptive Lasso and its Oracle property. J. Am. Stat. Assoc. 101, 1418–1429 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Sahar Behzadi
    • 1
    Email author
  • Kateřina Hlaváčková-Schindler
    • 1
  • Claudia Plant
    • 1
    • 2
  1. 1.Faculty of Computer Science, Data MiningUniversity of ViennaViennaAustria
  2. 2.ds:UniVie, University of ViennaViennaAustria

Personalised recommendations