Abstract
Characteristic rules have been advocated for their ability to improve interpretability over discriminative rules within the area of rule learning. However, the former type of rule has not yet been used by techniques for explaining predictions. A novel explanation technique, called CEGA (Characteristic Explanatory General Association rules), is proposed, which employs association rule mining to aggregate multiple explanations generated by any standard local explanation technique into a set of characteristic rules. An empirical investigation is presented, in which CEGA is compared to two state-of-the-art methods, Anchors and GLocalX, for producing local and aggregated explanations in the form of discriminative rules. The results suggest that the proposed approach provides a better trade-off between fidelity and complexity compared to the two state-of-the-art approaches; CEGA and Anchors significantly outperform GLocalX with respect to fidelity, while CEGA and GLocalX significantly outperform Anchors with respect to the number of generated rules. The effect of changing the format of the explanations of CEGA to discriminative rules and using LIME and SHAP as local explanation techniques instead of Anchors are also investigated. The results show that the characteristic explanatory rules still compete favorably with rules in the standard discriminative format. The results also indicate that using CEGA in combination with either SHAP or Anchors consistently leads to a higher fidelity compared to using LIME as the local explanation technique.
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
Notes
- 1.
All the datasets were obtained from https://www.openml.org except Adult, German credit, and Compas.
- 2.
- 3.
CEGA is available at: https://github.com/amrmalkhatib/CEGA.
References
Ribeiro, M., Singh, S., Guestrin, C.: “Why should I trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016, pp. 1135–1144 (2016)
Lundberg, S., Lee, S.: A unified approach to interpreting model predictions. Adv. Neural. Inf. Process. Syst. 30, 4765–4774 (2017)
Ribeiro, M., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: AAAI Conference on Artificial Intelligence (AAAI) (2018)
Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of the 20th International Conference on Very Large Data Bases, pp. 487–499 (1994)
Kohavi, R., Becker, B., Sommerfield, D.: Improving simple Bayes. In: European Conference On Machine Learning (1997)
Linardatos, P., Papastefanopoulos, V., Kotsiantis, S.: Explainable AI: a review of machine learning interpretability methods. Entropy 23 (2021)
Molnar, C.: Interpretable machine learning: a guide for making black box models explainable (2019)
Delaunay, J., Galárraga, L., Largouët, C.: Improving anchor-based explanations. In: CIKM 2020–29th ACM International Conference on Information and Knowledge Management, pp. 3269–3272, October 2020
Natesan Ramamurthy, K., Vinzamuri, B., Zhang, Y., Dhurandhar, A.: Model agnostic multilevel explanations. Adv. Neural. Inf. Process. Syst. 33, 5968–5979 (2020)
Setzu, M., Guidotti, R., Monreale, A., Turini, F., Pedreschi, D., Giannotti, F.: GLocalX - from local to global explanations of black box AI models. Artif. Intell. 294, 103457 (2021)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system (2016,8)
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 (2018)
Boström, H., Gurung, R., Lindgren, T., Johansson, U.: Explaining random forest predictions with association rules. Arch. Data Sci. Ser. A (Online First). 5, A05, 20 S. online (2018)
Bénard, C., Biau, G., Veiga, S., Scornet, E.: Interpretable random forests via rule extraction. In: Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, vol. 130, pp. 937–945, 13 April 2021
Friedman, J., Popescu, B.: Predictive learning via rule ensembles. Ann. Appl. Stat. 2, 916–954 (2008)
Ribeiro, M., Singh, S., Guestrin, C.: Model-agnostic interpretability of machine learning. In: ICML Workshop on Human Interpretability in Machine Learning (WHI) (2016)
Fürnkranz, J., Kliegr, T., Paulheim, H.: On cognitive preferences and the plausibility of rule-based models. Mach. Learn. 109(4), 853–898 (2020). https://doi.org/10.1007/s10994-019-05856-5
Kliegr, T., Bahník, Š, Fürnkranz, J.: A review of possible effects of cognitive biases on interpretation of rule-based machine learning models. Artif. Intell. 295, 103458 (2021)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 3145–3153, 6 August 2017
Wang, Z., et al.: CNN explainer: learning convolutional neural networks with interactive visualization. IEEE Trans. Visual. Comput. Graph. (TVCG) (2020)
Turmeaux, T., Salleb, A., Vrain, C., Cassard, D.: Learning characteristic rules relying on quantified paths. In: Knowledge Discovery in Databases: PKDD 2003, 7th European Conference On Principles and Practice of Knowledge Discovery in Databases, Cavtat-Dubrovnik, Croatia, 22–26 September 2003, Proceedings, vol. 2838, pp. 471–482 (2003)
Clark, P., Boswell, R.: Rule induction with CN2: some recent improvements. In: Kodratoff, Y. (ed.) EWSL 1991. LNCS, vol. 482, pp. 151–163. Springer, Heidelberg (1991). https://doi.org/10.1007/BFb0017011
Cohen, W.: Fast effective rule induction. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 115–123 (1995)
Friedman, J., Fisher, N.: Bump hunting in high-dimensional data. Stat. Comput. 9, 123–143, Apr 1999. https://doi.org/10.1023/A:1008894516817
Deng, H.: Interpreting tree ensembles with in Trees. Int. J. Data Sci. Anal. 7(4), 277–287 (2018). https://doi.org/10.1007/s41060-018-0144-8
Friedman, M.: A correction: the use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Am. Stat. Assoc. 34, 109–109 (1939)
Nemenyi, P.: Distribution-Free Multiple Comparisons. Princeton University (1963)
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1(6), 80–83 (1945). http://www.Jstor.Org/stable/3001968
Slack, D., Hilgard, S., Jia, E., Singh, S., Lakkaraju, H.: Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods. In: AAAI/ACM Conference on AI, Ethics, and Society (AIES) (2020)
Loyola-González, O.: Black-box vs. white-box: understanding their advantages and weaknesses from a practical point of view. IEEE Access 7, 154096–154113 (2019)
Fürnkranz, J., Gamberger, D., Lavrac, N.: Foundations of Rule Learning. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-540-75197-7
Michalski, R.: A theory and methodology of inductive learning. Artif. Intell. 20, 111–161 (1983). https://www.sciencedirect.com/science/article/pii/0004370283900164
Acknowledgement
This work was partially supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. HB was partly funded by the Swedish Foundation for Strategic Research (CDA, grant no. BD15-0006).
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
Alkhatib, A., Boström, H., Vazirgiannis, M. (2023). Explaining Predictions by Characteristic Rules. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13713. Springer, Cham. https://doi.org/10.1007/978-3-031-26387-3_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-26387-3_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26386-6
Online ISBN: 978-3-031-26387-3
eBook Packages: Computer ScienceComputer Science (R0)
