Advertisement

ALIME: Autoencoder Based Approach for Local Interpretability

  • Sharath M. ShankaranarayanaEmail author
  • Davor Runje
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11871)

Abstract

Machine learning and especially deep learning have garnered tremendous popularity in recent years due to their increased performance over other methods. The availability of large amount of data has aided in the progress of deep learning. Nevertheless, deep learning models are opaque and often seen as black boxes. Thus, there is an inherent need to make the models interpretable, especially so in the medical domain. In this work, we propose a locally interpretable method, which is inspired by one of the recent tools that has gained a lot of interest, called local interpretable model-agnostic explanations (LIME). LIME generates single instance level explanation by artificially generating a dataset around the instance (by randomly sampling and using perturbations) and then training a local linear interpretable model. One of the major issues in LIME is the instability in the generated explanation, which is caused due to the randomly generated dataset. Another issue in these kind of local interpretable models is the local fidelity. We propose novel modifications to LIME by employing an autoencoder, which serves as a better weighting function for the local model. We perform extensive comparisons with different datasets and show that our proposed method results in both improved stability, as well as local fidelity.

Keywords

Interpretable machine learning Deep learning Autoencoder Explainable AI (XAI) Healthcare 

References

  1. 1.
    Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems, pp. 153–160 (2007)Google Scholar
  2. 2.
    Bien, J., Tibshirani, R., et al.: Prototype selection for interpretable classification. Ann. Appl. Stat. 5(4), 2403–2424 (2011)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Diaconis, P., Efron, B.: Computer-intensive methods in statistics. Sci. Am. 248(5), 116–131 (1983)CrossRefGoogle Scholar
  4. 4.
    Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
  5. 5.
    Hall, P., Gill, N., Kurka, M., Phan, W.: Machine learning interpretability with H2O driverless AI, February 2019. http://docs.h2o.ai
  6. 6.
    Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1885–1894 (2017). JMLR.org
  7. 7.
    Lakkaraju, H., Bach, S.H., Leskovec, J.: Interpretable decision sets: a joint framework for description and prediction. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2016)Google Scholar
  8. 8.
    Laugel, T., Renard, X., Lesot, M.J., Marsala, C., Detyniecki, M.: Defining locality for surrogates in post-hoc interpretablity. arXiv preprint arXiv:1806.07498 (2018)
  9. 9.
    Mangasarian, O.L., Street, W.N., Wolberg, W.H.: Breast cancer diagnosis and prognosis via linear programming. Oper. Res. 43(4), 570–577 (1995)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Molnar, C.: Interpretable machine learning (2019). https://christophm.github.io/interpretable-ml-book/
  11. 11.
    Ramana, B.V., Babu, M.S.P., Venkateswarlu, N., et al.: A critical study of selected classification algorithms for liver disease diagnosis. Int. J. Database Manag. Syst. 3(2), 101–114 (2011)CrossRefGoogle Scholar
  12. 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. ACM (2016)Google Scholar
  13. 13.
    Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  14. 14.
    Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103. ACM (2008)Google Scholar
  15. 15.
    Zafar, M.R., Khan, N.M.: DLIME: a deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems. In: In Proceeding of ACM SIGKDD Workshop on Explainable AI/ML (XAI) for Accountability, Fairness, and Transparency. ACM, Anchorage (2019)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.ZASTI.AIChennaiIndia

Personalised recommendations