Abstract
Due to the high precision and the huge prediction needs, machine learning models based decision systems has been widely adopted in all works of life. They were usually constructed as a black box based on sophisticated, opaque learning models. The lack of human understandable explanation to the inner logic of these models and the reason behind the predictions from such systems causes a serious trust issue. Interpretable Machine Learning methods can be used to relieve this problem by providing an explanation for the models or predictions. In this work, we focus on the model explanation problem, which study how to explain the black box prediction model globally through human understandable explanation. We propose the Influence Function based Model Explanation (IFME) method to provide interpretable model explanation based on key training points selected through influence function. First, our method introduces a novel local prediction interpreter, which also utilizes the key training points for local prediction. Then it finds the key training points to the learning models via influence function globally. Finally, we provide the influence function based model agnostic explanation to the model used. We also show the efficiency of our method through both theoretical analysis and simulated experiments.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Blitzer, J., Dredze, M., Pereira, F.: Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 440–447. Association for Computational Linguistics, Prague, Czech Republic, June 2007. https://www.aclweb.org/anthology/P07-1056
Cook, R.D.: Detection of influential observation in linear regression. Technometrics 19(1), 15–18 (1977). https://doi.org/10.2307/1268249
Dhaliwal, J., Shintre, S.: Gradient similarity: an explainable approach to detect adversarial attacks against deep learning (2018). http://arxiv.org/abs/1806.10707
Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3449–3457. IEEE (2017). https://doi.org/10.1109/ICCV.2017.371
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(5), 93:1–93:42 (2019). https://doi.org/10.1145/3236009
Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. In: Proceedings of the 34th International Conference on Machine Learning. ICML 2017, vol. 70, pp. 1885–1894 (2017). http://dl.acm.org/citation.cfm?id=3305381.3305576
Lou, Y., Caruana, R., Gehrke, J., Hooker, G.: Accurate intelligible models with pairwise interactions. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2013, p. 623. ACM Press (2013). http://dl.acm.org/citation.cfm?doid=2487575.2487579
Martens, D., Provost, F.: Explaining data-driven document classifications. Mis Q. 38(1), 73–100 (2013)
Sonnenburg, S., Zien, A., Philips, P., Rätsch, G.: POIMs: positional oligomer importance matrices-understanding support vector machine-based signal detectors. Bioinformatics 24(13), i6–i14 (2008). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2718648/
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention (2015). http://arxiv.org/abs/1502.03044
Zien, A., Krämer, N., Sonnenburg, S., Rätsch, G.: The feature importance ranking measure. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009. LNCS (LNAI), vol. 5782, pp. 694–709. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04174-7_45
Zintgraf, L.M., Cohen, T.S., Adel, T., Welling, M.: Visualizing deep neural network decisions: prediction difference analysis (2017). http://arxiv.org/abs/1702.04595
Acknowledgments
This study was supported by the National Key Research and Development Plan’s Key Special Program on High performance computing of China, No. 2017YFB0203201.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zha, B., Shen, H. (2020). IFME: Influence Function Based Model Explanation for Black Box Decision Systems. In: Shen, H., Sang, Y. (eds) Parallel Architectures, Algorithms and Programming. PAAP 2019. Communications in Computer and Information Science, vol 1163. Springer, Singapore. https://doi.org/10.1007/978-981-15-2767-8_27
Download citation
DOI: https://doi.org/10.1007/978-981-15-2767-8_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2766-1
Online ISBN: 978-981-15-2767-8
eBook Packages: Computer ScienceComputer Science (R0)