Towards Scalable and Robust Sum-Product Networks

  • Alvaro H. C. Correia
  • Cassio P. de CamposEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11940)


Sum-Product Networks (SPNs) and their credal counterparts are machine learning models that combine good representational power with tractable inference. Yet they often have thousands of nodes which result in high processing times. We propose the addition of caches to the SPN nodes and show how this memoisation technique reduces inference times in a range of experiments. Moreover, we introduce class-selective SPNs, an architecture that is suited for classification tasks and enables efficient robustness computation in Credal SPNs. We also illustrate how robustness estimates relate to reliability through the accuracy of the model, and how one can explore robustness in ensemble modelling.


Sum-Product Networks Robustness 


  1. 1.
    Amer, M.R., Todorovic, S.: Sum product networks for activity recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(4), 800–813 (2016)CrossRefGoogle Scholar
  2. 2.
    Chen, T., Guestrin, C.: XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 19, no. (6), pp. 785–794 (2016)Google Scholar
  3. 3.
    Cheng, W.C., Kok, S., Pham, H.V., Chieu, H.L., Chai, K.M.A.: Language modeling with sum-product networks. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 2098–2102 (2014)Google Scholar
  4. 4.
    Darwiche, A.: A differential approach to inference in bayesian networks. J. ACM 50(3), 280–305 (2003)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Delalleau, O., Bengio, Y.: Shallow vs. deep sum-product networks. In: Advances in Neural Information Processing Systems, vol. 24. pp. 666–674. Curran Associates, Inc. (2011)Google Scholar
  6. 6.
    Gens, R., Domingos, P.: Learning the structure of sum-product networks. In: Proceedings of the 30th International Conference on Machine Learning, vol. 28, pp. 229–264 (2013)Google Scholar
  7. 7.
    Korte, B., Vygen, J.: Combinatorial Optimization: Theory and Algorithms, 5th edn. Springer Publishing Company, Incorporated, Heidelberg (2012)CrossRefGoogle Scholar
  8. 8.
    Lichman, M.: UCI machine learning repository (2013).
  9. 9.
    Maua, D.D., Conaty, D., Cozman, F.G., Poppenhaeger, K., de Campos, P.C.: Robustifying sum-product networks. Int. J. Approximate Reasoning 101, 163–180 (2018)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Mei, J., Jiang, Y., Tu, K.: Maximum a posteriori inference in sum-product networks. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  11. 11.
    Nath, A., Domingos, P.: Learning tractable probabilistic models for fault localization. In: 30th AAAI Conference on Artificial Intelligence, AAAI 2016, pp. 1294–1301 (2016)Google Scholar
  12. 12.
    Peharz, R.: Foundations of Sum-Product Networks for Probabilistic Modeling. Ph.D. thesis, Graz University of Technology (2015)Google Scholar
  13. 13.
    Peharz, R., Gens, R., Domingos, P.: Learning selective sum-product networks. In: Proceedings of the 31st International Conference on Machine Learning, vol. 32 (2014)Google Scholar
  14. 14.
    Peharz, R., Tschiatschek, S., Pernkopf, F., Domingos, P.: On Theoretical Properties of Sum-Product Networks. In: Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS), vol. 38, pp. 744–752 (2015)Google Scholar
  15. 15.
    Poon, H., Domingos, P.: Sum product networks: a new deep architecture. In: 2011 IEEE International Conference on Computer Vision Workshops (2011)Google Scholar
  16. 16.
    Pronobis, A., Rao, R.P.: Learning deep generative spatial models for mobile robots. In: IEEE International Conference on Intelligent Robots and Systems, pp. 755–762 (2017)Google Scholar
  17. 17.
    Sguerra, B.M., Cozman, F.G.: Image classification using sum-product networks for autonomous flight of micro aerial vehicles. In: 2016 5th Brazilian Conference on Intelligent Systems (BRACIS), pp. 139–144 (2016)Google Scholar
  18. 18.
    Wang, J., Wang, G.: Hierarchical spatial sum-product networks for action recognition in still images. IEEE Trans. Circuits Syst. Video Technol. 28(1), 90–100 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Eindhoven University of TechnologyEindhovenThe Netherlands

Personalised recommendations