Abstract
Machine learning models are ubiquitous today in most application domains and are often taken for granted. While integrated into many systems, oftentimes even unnoticed by the user, these powerful models frequently remain as black-boxes. They are black-boxes because while they are powerful predictive models, it is commonly the case that one cannot understand the decision-making process behind their predictions. Even if we understand the inner workings of a learning algorithm building a predictive model, the mechanism during inference is more often than not obscure. How can we trust that a certain prediction from a model is correct? How can we trust that the model is making reasonable predictions in general? Debugging a predictive model is unworkable in the absence of explanations.
We propose herein a new framework, called BARBE, a model-independent explainer, that learns a surrogate rule-based model on data labeled by the black-box. BARBE makes use of an interpretable associative classifier to create a rule-based model that provides various explanations, including salient features, associations between features, and rule-based representations. Our experimental analysis illustrates the effectiveness of BARBE in generating rule-based explanations for both numerical and text data, when compared to state-of-the-art explainers. Our study demonstrates the faithfulness of BARBE to black-box models. The text-based explanations generated by BARBE are more meaningful to show the fidelity and trustworthiness of the explanation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We use scikit-learn [18] for implementing the DT.
- 2.
We used the implementation in https://github.com/changyaochen/rbo.
References
General data protection regulation (2020). https://en.wikipedia.org/wiki/General_Data_Protection_Regulation
Agrawal, R., Srikant, R., et al.: Fast algorithms for mining association rules. In: International Conference on VLDB, vol. 1215, pp. 487–499 (1994)
Antonie, M.L., Zaiane, O.R.: Text document categorization by term association. In: IEEE International Conference on Data Mining, pp. 19–26. IEEE (2002)
Cohen, W.W.: Fast effective rule induction. In: Twelfth International Conference on Machine Learning (1995)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., Giannotti, F.: Local rule-based explanations of black box decision systems. arXiv preprint arXiv:1805.10820 (2018)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 93 (2018)
Hamalainen, W.: Efficient discovery of the top-k optimal dependency rules with fisher’s exact test of significance. In: 2010 IEEE International Conference on Data Mining, pp. 196–205. IEEE (2010)
Han, J., Pei, J., Yin, Y.: Mining frequent patterns without candidate generation. In: ACM Sigmod Record, vol. 29, pp. 1–12 (2000)
Jia, Y., Bailey, J., Ramamohanarao, K., Leckie, C., Ma, X.: Exploiting patterns to explain individual predictions. Knowl. Inf. Syst. 62, 927–950 (2019). https://doi.org/10.1007/s10115-019-01368-9
Li, J., Zaiane, O.R.: Exploiting statistically significant dependent rules for associative classification. Intell. Data Anal. 21(5), 1155–1172 (2017)
Li, W., Han, J., Pei, J.: CMAR: accurate and efficient classification based on multiple class-association rules. In: Proceedings 2001 IEEE International Conference on Data Mining, pp. 369–376. IEEE (2001)
Liu, B., Hsu, W., Ma, Y., et al.: Integrating classification and association rule mining. In: KDD, vol. 98, pp. 80–86 (1998)
Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142–150 (2011)
Meddahi, K., et al.: Towards a co-selection approach for a global explainability of black box machine learning models. In: Chbeir, R., Huang, H., Silvestri, F., Manolopoulos, Y., Zhang, Y. (eds.) WISE 2022. Lecture Notes in Computer Science, vol. 13724, pp. 97–109. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20891-1_8
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1–38 (2018)
Pastor, E., Baralis, E.: Explaining black box models by means of local rules. In: Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, pp. 510–517 (2019)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Poulin, B., et al.: Visual explanation of evidence with additive classifiers. In: Proceedings of the National Conference on Artificial Intelligence, vol. 21, p. 1822. AAAI Press, MIT Press, Menlo Park, Cambridge, London (2006)
Ramos, J., et al.: Using TF-IDF to determine word relevance in document queries. In: Proceedings of the first instructional conference on machine learning, vol. 242, pp. 29–48. Citeseer (2003)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier. In: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Secretariat, T.B.O.C.: Directive on automated decision-making (2017). https://www.tbs-sct.gc.ca/pol/doc-eng.aspx?id=32592
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Shahroudnejad, A.: A survey on understanding, visualizations, and explanation of deep neural networks. preprint arXiv:2102.01792 (2021)
Sukel, K.: Artificial intelligence ushers in the era of superhuman doctors (2017). https://www.newscientist.com/article/mg23531340-800-artificial-intelligence-ushers-in-the-era-of-superhuman-doctors/
Webber, W., Moffat, A., Zobel, J.: A similarity measure for indefinite rankings. ACM Trans. Inf. Syst. (TOIS) 28(4), 1–38 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Motallebi, M., Anik, M.T.A., Zaïane, O.R. (2023). Explaining Decisions of Black-Box Models Using BARBE. In: Strauss, C., Amagasa, T., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Database and Expert Systems Applications. DEXA 2023. Lecture Notes in Computer Science, vol 14147. Springer, Cham. https://doi.org/10.1007/978-3-031-39821-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-39821-6_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39820-9
Online ISBN: 978-3-031-39821-6
eBook Packages: Computer ScienceComputer Science (R0)