Skip to main content

Explanation-Driven Model Stacking

  • 839 Accesses

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 12747)

Abstract

With advances of artificial intelligence (AI), there is a growing need for provisioning of transparency and accountability to AI systems. These properties can be achieved with eXplainable AI (XAI) methods, extensively developed over the last few years with relation for machine learning (ML) models. However, the practical usage of XAI is limited nowadays in most of the cases to the feature engineering phase of the data mining (DM) process. We argue that explainability as a property of a system should be used along with other quality metrics such as accuracy, precision, recall in order to deliver better AI models. In this paper we present a method that allows for weighted ML model stacking and demonstrates its practical use in an illustrative example.

Keywords

  • Explainability
  • Machine learning
  • Optimization

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-77980-1_28
  • Chapter length: 11 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-77980-1
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   109.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

Notes

  1. 1.

    See: https://github.com/sbobek/inxai.

  2. 2.

    See https://scikit-learn.org.

  3. 3.

    See: https://eli5.readthedocs.io/en/latest/blackbox.

  4. 4.

    For source code see: https://github.com/mozo64/inxai/blob/main/examples/xai_on_synth_data/XAI-boost-on-syntetic-data-v4.ipynb.

  5. 5.

    See: https://automl.github.io/.

References

  1. Almeida, A., Lopez-de Ipina, D.: Assessing ambiguity of context data in intelligent environments: towards a more reliable context managing systems. Sensors 12(4), 4934–4951 (2012). http://www.mdpi.com/1424-8220/12/4/4934

  2. Alvarez-Melis, D., Jaakkola, T.S.: On the robustness of interpretability methods (2018)

    Google Scholar 

  3. Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2020)

    CrossRef  Google Scholar 

  4. DARPA: Broad agency announcement - explainable artificial intelligence (XAI). DARPA-BAA-16-53 (Aug 2016)

    Google Scholar 

  5. Dey, A.K.: Modeling and intelligibility in ambient environments. J. Ambient Intell. Smart Environ. 1(1), 57–62 (2009)

    CrossRef  Google Scholar 

  6. Goodman, B., Flaxman, S.: European union regulations on algorithmic decision-making and a “right to explanation”. arXiv preprint arXiv:1606.08813 (2016)

  7. Hutter, F., Hoos, H.H., Leyton-Brown, K.: Sequential model-based optimization for general algorithm configuration (extended version). Technical report. TR-2010-10, University of British Columbia, Department of Computer Science (2010). http://www.cs.ubc.ca/~hutter/papers/10-TR-SMAC.pdf

  8. Jannach, D., Manzoor, A., Cai, W., Chen, L.: A survey on conversational recommender systems (2020)

    Google Scholar 

  9. Lim, B.Y., Dey, A.K., Avrahami, D.: Why and why not explanations improve the intelligibility of context-aware intelligent systems. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 2119–2128, CHI 2009. ACM, New York (2009). https://doi.org/10.1145/1518701.1519023

  10. Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4768–4777. NIPS2017, Curran Associates Inc. (2017)

    Google Scholar 

  11. Mohseni, S., Zarei, N., Ragan, E.D.: A multidisciplinary survey and framework for design and evaluation of explainable AI systems (2020)

    Google Scholar 

  12. Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144, KDD 2016. Association for Computing Machinery, New York (2016). https://doi.org/10.1145/2939672.2939778

  13. Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: AAAI Publications, Thirty-Second AAAI Conference on Artificial Intelligence (2018)

    Google Scholar 

  14. Robnik-Šikonja, M., Bohanec, M.: Perturbation-based explanations of prediction models. In: Zhou, J., Chen, F. (eds.) Human and Machine Learning. HIS, pp. 159–175. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-90403-0_9

    CrossRef  Google Scholar 

  15. Roy, N., Das, S.K., Julien, C.: Resource-optimized quality-assured ambiguous context mediation framework in pervasive environments. IEEE Trans. Mob. Comput. 11(2), 218–229 (2012). http://dblp.uni-trier.de/db/journals/tmc/tmc11.html#RoyDJ12

  16. Schank, R.C.: Explanation: A first pass. In: Kolodner, J.L., Riesbeck, C.K. (eds.) Experience, Memory, and Reasoning, pp. 139–165. Lawrence Erlbaum Associates, Hillsdale (1986)

    Google Scholar 

  17. Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D.: Grad-cam: Why did you say that? visual explanations from deep networks via gradient-based localization. CoRR abs/1610.02391 (2016). http://arxiv.org/abs/1610.02391

  18. Sokol, K., Flach, P.A.: Explainability fact sheets: A framework for systematic assessment of explainable approaches. CoRR abs/1912.05100 (2019)

    Google Scholar 

  19. Yeh, C.K., Hsieh, C.Y., Suggala, A.S., Inouye, D.I., Ravikumar, P.: On the (in)fidelity and sensitivity for explanations (2019)

    Google Scholar 

Download references

Acknowledgements

The paper is funded from the PACMEL project funded by the National Science Centre, Poland under CHIST-ERA programme (NCN 2018/27/Z/ST6/03392). The authors are grateful to ACK Cyfronet, Krakow for granting access to the computing infrastructure built in the projects No. POIG.02.03.00-00-028/08 “PLATON - Science Services Platform” and No. POIG.02.03.00-00-110/13 “Deploying high-availability, critical services in Metropolitan Area Networks (MAN-HA)”.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Szymon Bobek .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Bobek, S., Mozolewski, M., Nalepa, G.J. (2021). Explanation-Driven Model Stacking. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12747. Springer, Cham. https://doi.org/10.1007/978-3-030-77980-1_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-77980-1_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-77979-5

  • Online ISBN: 978-3-030-77980-1

  • eBook Packages: Computer ScienceComputer Science (R0)