Abstract
Post-hoc techniques represent a vast collection of methods created to specifically address the black-box problem, where we do not have access to the internal feature representations or model structure. There are considerable advantages to using post-hoc methods. They can work for a wide variety of model algorithms. They allow for different representations to be used for internal modeling and explanation. They can also provide different types of explanations for the same model. However, there is a trade-off between the fidelity and comprehensibility of explanations.
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
References
A. Fisher, C. Rudin, F. Dominici, All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously (2019). arXiv:1801.01489 [stat.ME]
J.H. Friedman, B.E. Popescu, Predictive learning via rule ensembles. Ann. Appl. Stat. 2(3) (2008). ISSN: 1932-6157. http://dx.doi.org/10.1214/07-AOAS148
S. Lundberg, S.-I. Lee, A unified approach to interpreting model predictions (2017). arXiv:1705.07874 [cs.AI].
M.T. Ribeiro, S. Singh, C. Guestrin, “Why should I trust you?”: explaining the predictions of any classifier (2016). arXiv:1602.04938 [cs.LG]
L.S. Shapley, A value for n-person games, in Contributions to the Theory of Games (AM-28), Volume II, ed. by H.W. Kuhn, A.W. Tucker (Princeton University Press, Princeton, 1953). ISBN: 978-1-40088-197-0
D. Slack et al., Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods (2020). arXiv:1911.02508 [cs.LG]
M. Sundararajan, A. Najmi, The many Shapley values for model explanation (2019). arxiv:1908.08474, Comment: 9 pages
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kamath, U., Liu, J. (2021). Post-Hoc Interpretability and Explanations. In: Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-030-83356-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-83356-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-83355-8
Online ISBN: 978-3-030-83356-5
eBook Packages: Computer ScienceComputer Science (R0)