Abstract
In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for mixed model types, a framework for layer wise propagation of Shapley values that builds upon DeepLIFT (an existing approach for explaining neural networks). We show that in addition to being able to explain neural networks, this new framework naturally enables attributions for stacks of mixed models (e.g., neural network feature extractor into a tree model) as well as attributions of the loss. Finally, we theoretically justify a method for obtaining attributions with respect to a background distribution (under a Shapley value framework).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Goodman, B., Flaxman, S.: AI Magazine 38(3), 50 (2017)
Holzinger, A., Biemann, C., Pattichis, C.S., Kell, D.B., arXiv preprint arXiv:1712.09923 (2017)
Lundberg, S.M., Erion, G., Chen, H., DeGrave, A., Prutkin, J.M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., Lee, S.: CoRR abs/1905.04610http://arxiv.org/abs/1905.04610 (2018)
Lundberg, S.M., Nair, B., Vavilala, M.S., Horibe, M., Eisses, M.J., Adams, T., Liston, D.E., Low, D.K.W., Newman, S.F., Kim, J., Lee, S.I.: bioRxiv. 10.1101/206540. https://www.biorxiv.org/content/early/2017/10/21/206540 (2017)
Arcadu, F., Benmansour, F., Maunz, A., Willis, J., Haskova, Z., Prunotto, M.: NPJ Dig. Med. 2(1), 1 (2019)
Lundberg, S.M., Lee, S.I.: Advances in Neural Information Processing Systems, pp. 4765–4774 (2017)
Shapley, L.S.: Contributions to the Theory of Games 2(28), 307 (1953)
Å trumbelj, E., Kononenko, I.: Knowl. Inf. Syst. 41(3), 647 (2014)
Zeiler, M.D., Fergus, R.: European Conference on Computer Vision, pp. 818–833. Springer (2014)
Simonyan, K., Vedaldi, A., Zisserman, A.: arXiv preprint arXiv:1312.6034 (2013)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.R., Samek, W.: PLoS One 10(7), e0130140 (2015)
Sundararajan,, M., Taly, A., Yan, Q.: arXiv preprint arXiv:1703.01365 (2017)
Merrill, J., Ward, G., Kamkar, S., Budzik, J., Merrill, D.: CoRR abs/1909.01869http://arxiv.org/abs/1909.01869 (2019)
Ancona, M., Öztireli, C., Gross, M.: arXiv preprint arXiv:1903.10992 (2019)
Shrikumar, A., Greenside, P., Kundaje, A.: Proceedings of the 34th International Conference on Machine Learning, vol. 70 (JMLR.org), pp. 3145–3153 (2017)
Ancona, M., Ceolini, E., Oztireli, C., Gross, M.: 6th International Conference on Learning Representations (ICLR 2018) (2018)
Erion, G., Janizek, J.D., Sturmfels, P., Lundberg, S., Lee, S.I.: arXiv preprint arXiv:1906.10670 (2019)
Janzing, D., Minorics, L., Blöbaum, P.: arXiv preprint arXiv:1910.13413 (2019)
Sundararajan, M., Najmi, A.: arXiv preprint arXiv:1908.08474 (2019)
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, Citeseer (2009)
Cox, C.S., Feldman, J.J., Golden, C.D., Lane, M.A., Madans, J.H., Mussolino, M.E., Rothwell, S.T.: Vital and Health Statistics (1997)
Gjonça, A., Tomassini, C., Vaupel, J.W., et al.: Male-female differences in mortality in the developed world, Citeseer (1999)
Port, S., Demer, L., Jennrich, R., Walter, D., Garfinkel, A.: The Lancet 355(9199), 175 (2000)
Goldwasser, P., Feldman, J.: J. Clin. Epidemiol. 50(6), 693 (1997)
Paul, L., Jeemon, P., Hewitt, J., McCallum, L., Higgins, P., Walters, M., McClure, J., Dawson, J., Meredith, P., Jones, G.C., et al.: Hypertension 60(3), 631 (2012)
Go, D.J., Lee, E.Y., Lee, E.B., Song, Y.W., Konig, M.F., Park, J.K.: J. Korean Med. Sci. 31(3), 389 (2016)
Bao, X., Bergman, L., Thompson, R.: Proceedings of the Third ACM Conference on Recommender Systems, pp. 109–116. ACM (2009)
Güneş, F., Wolfinger, R., Tan, P.Y.: SAS Conference Proceedings (2017)
Zhai, B., Chen, J.: Sci. Total Environ. 635, 644 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Chen, H., Lundberg, S., Lee, SI. (2021). Explaining Models by Propagating Shapley Values of Local Components. In: Shaban-Nejad, A., Michalowski, M., Buckeridge, D.L. (eds) Explainable AI in Healthcare and Medicine. Studies in Computational Intelligence, vol 914. Springer, Cham. https://doi.org/10.1007/978-3-030-53352-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-53352-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-53351-9
Online ISBN: 978-3-030-53352-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)