Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Physics-Informed Radial Basis Function Networks: Solving Inverse Problems for Partial Differential Equations Read chapter Read first chapter

2023 | OriginalPaper | Chapter

Modifications of SHAP for Local Explanation of Function-Valued Predictions Using the Divergence Measures

Authors : Lev Utkin, Artem Petrov, Andrei Konstantinov

Published in: Cyber-Physical Systems and Control II

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Modifications of the well-known SHAP method for the local explanation of black-box classification models are proposed. It is supposed that the classifier prediction is represented in the form of a class probability distribution. A key idea behind the modifications is to replace the difference of characteristic functions in the framework of Shapley values with non-symmetric divergence measures between the predicted class probability distribution with a feature and without it. Such measures are used for estimating the feature contribution, for example, the Kullback-Leibler divergence and Chi-squared-divergence. For comparison purposes, we also study the symmetric Hellinger distance measure. A lot of numerical experiments on synthetic and real datasets illustrating the proposed modifications are provided and analyzed.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Control of Plane Poiseuille Flow Using the Kreiss Constant
next chapter Robust Models of Distance Metric Learning by Interval-Valued Training Data
Literature
1.
Holzinger, A., Langs, G., Denk, H., Zatloukal, K., Muller, H.: Causability and explainability of artificial intelligence in medicine. WIREs Data Min. Knowl. Discov. 9, e1312 (2019)
2.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51, 93 (2019)CrossRef
3.
Liang, Y., Li, S., Yan, C., Li, M., Jiang, C.: Explaining the black-box model: a survey of local interpretation methods for deep neural networks. Neurocomputing 419, 168–182 (2021)CrossRef
4.
Xie, N., Ras, G., van Gerven, M., Doran, D.: Explainable deep learning: a field guide for the uninitiated (2020). arXiv:​2004.​14545. Accessed 24 Mar 2021
5.
Hendricks, L.A., Hu, R., Darrell, T., Akata, Z.: Grounding visual explanations. In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds.) Proceedings of the 15th European Conference on Computer Vision – ECCV 2018, Munich, Germany, September 8–14, 2018, Part II. Lecture Notes in Computer Science, vol. 11206, pp. 269–286. Springer, Cham (2018).https://​doi.​org/​10.​1007/​978-3-030-01216-8_​17
6.
Arras, L., Arjona-Medina, J., Widrich, M., Montavon, G., Gillhofer, M., Muller, K.R., Hochreiter, S., Samek, W.: Explaining and interpreting LSTMs (2019). arXiv:​1909.​12114. Accessed 24 Mar 2021
7.
8.
Ribeiro, M., Singh, S., Guestrin, C.: “Why should I trust You?” Explaining the predictions of any classifier (2016). arXiv:​1602.​04938v3. Accessed 24 Mar 2021
9.
10.
Huang, Q., Yamada, M., Tian, Y., Singh, D., Yin, D., Chang, Y.: GraphLIME: local interpretable model explanations for graph neural networks (2020). arXiv:​2001.​06216. Accessed 24 Mar 2021
11.
Kovalev, M., Utkin, L., Kasimov, E.: SurvLIME: a method for explaining machine learning survival models. Knowl.-Based Syst. 203, 106164 (2020)CrossRef
12.
13.
Strumbelj, E., Kononenko, I.: An efficient explanation of individual classifications using game theory. J. Mach. Learn. Res. 11, 1–18 (2010)MATH
14.
Shapley, L.: A value for n-person games. In: Contributions to the Theory of Games. Volume II of Annals of Mathematics Studies, vol. 28, pp. 307–317. Princeton University Press, Princeton (1953)
15.
16.
Yuan, H., Yu, H., Wang, J., Li, K., Ji, S.: On explainability of graph neural networks via subgraph explorations (2020). arXiv:​2102.​05152. Accessed 24 Mar 2021
17.
Frye, C., de Mijolla, D., Cowton, L., Stanley, M., Feige, I.: Shapley-based explainability on the data manifold (2020). arXiv:​2006.​01272. Accessed 24 Mar 2021
18.
Bowen, D., Ungar, L.: Generalized SHAP: generating multiple types of explanations in machine learning (2020). arXiv:​2006.​07155v2. Accessed 24 Mar 2021
19.
Kullback, S., Leibler, R.: On information and sufficiency. Ann. Math. Stat. 22, 9–86 (1951)CrossRefMATH
20.
Covert, I., Lundberg, S., Lee, S.I.: Understanding global feature contributions with additive importance measures. (2020). arXiv:​2004.​00668v2. Accessed 24 Mar 2021
21.
Pearson, K.: On the criterion that a given system of eviations from the probable in the case of correlated system of variables is such that it can be reasonable supposed to have arisen from random sampling. Philos. Mag. 50, 157–172 (1900)CrossRefMATH
22.
Covert, I., Lundberg, S., Lee, S.I.: Explaining by removing: a unified framework for model explanation (2020). arXiv:​2011.​14878. Accessed 24 Mar 2021
23.
Petsiuk, V., Das, A., Saenko, K.: RISE: randomized input sampling for explanation of black-box models (2018). arXiv:​1806.​07421. Accessed 24 Mar 2021
24.
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds.) Computer Vision – ECCV 2014. ECCV 2014, Lecture Notes in Computer Science, vol. 8689, pp. 818–833. Springer, Cham (2014).https://​doi.​org/​10.​1007/​978-3-319-10590-1_​53
25.
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5505–5514 (2018). https://​arxiv.​org/​abs/​1801.​07892. Accessed 24 Mar 2021
26.
Jain, K., Chhabra, P.: Bounds on nonsymmetric divergence measure in terms of other symmetric and nonsymmetric divergence measures. Int. Sch. Res. Not. 2014, 1–9 (2014)
27.
Dragomir, S., Gluscevic, V., Pearce, C.: Approximations for the Csiszar’s fdivergence via midpoint inequalities. In: Inequality Theory and Applications, pp. 139–154. Nova Science Publishers Inc., Huntington, New York (2001)
28.
29.
Csiszar, I.: Information type measures of differences of probability distribution and indirect observations. Stud. Sci. Math. Hung. 2, 299–318 (1967)MATH
30.
Nielsen, F., Nock, R.: On the chi square and higher-order chi distances for approximating f-divergences. IEEE Signal Process. Lett. 21, 10–13 (2014)CrossRef
31.
Dragomir, S., Scholz, M., Sunde, J.: Some upper bounds for relative entropy and applications. Comput. Math. Appl. 39, 91–100 (2000)CrossRefMATH
32.
Chen, M., Sbert, M.: On the upper bound of the Kullback-Leibler divergence and cross entropy (2019). arXiv:​1911.​08334. Accessed 24 Mar 2021
Metadata
Title
Modifications of SHAP for Local Explanation of Function-Valued Predictions Using the Divergence Measures
Authors
Lev Utkin
Artem Petrov
Andrei Konstantinov
Copyright Year
2023
Book
Cyber-Physical Systems and Control II

Print ISBN: 978-3-031-20874-4

Electronic ISBN: 978-3-031-20875-1

Copyright Year: 2023

DOI
https://doi.org/10.1007/978-3-031-20875-1_6

Premium Partner

    Image Credits