Relevance Metric for Counterfactuals Selection in Decision Trees
Explainable Machine Learning is an emerging field in the Machine Learning domain. It addresses the explicability of Machine Learning models and the inherent rationale behind model predictions. In the particular case of example-based explanation methods, they are focused on using particular instances, previously defined or created, to explain the behaviour of models or predictions. Counterfactual-based explanation is one of these methods. A counterfactual is an hypothetical instance similar to an example whose explanation is of interest but with different predicted class. This paper presents a relevance metric for counterfactual selection called sGower designed to induce sparsity in Decision Trees models. It works with categorical and continuous features, while considering number of feature changes and distance between the counterfactual and the example. The proposed metric is evaluated against previous relevance metrics on several sets of categorical and continuous data, obtaining on average better results than previous approaches.
KeywordsExplainable Machine Learning Example-based Counterfactuals Decision Trees
Research supported by grant from the Spanish Ministry of Economy and Competitiveness: SABERMED (Ref: RTC-2017-6253-1); Retos-Investigación program: MODAS-IN (Ref: RTI2018-094269-B-I00); and NVIDIA Corporation.
- 1.Adhikari, A., Tax, D., Satta, R., Fath, M.: Example and feature importance-based explanations for black-box machine learning models. arXiv preprint arXiv:1812.09044 (2018)
- 2.Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
- 4.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)
- 5.Hall, P., Gill, N.: Introduction to Machine Learning Interpretability. O’Reilly Media, Sebastopol (2018)Google Scholar
- 6.Kim, B., Khanna, R., Koyejo, O.O.: Examples are not enough, learn to criticize! criticism for interpretability. In: Advances in Neural Information Processing Systems, pp. 2280–2288 (2016)Google Scholar
- 7.Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1885–1894. JMLR. org (2017)Google Scholar
- 8.Laugel, T., Lesot, M.J., Marsala, C., Renard, X., Detyniecki, M.: Inverse classification for comparison-based interpretability in machine learning. arXiv preprint arXiv:1712.08443 (2017)
- 10.Molnar, C.: Interpretable machine learning (2018) Google Scholar
- 11.Ribeiro, M.T., 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, pp. 1135–1144. ACM (2016)Google Scholar
- 12.Sokol, K., Flach, P.A.: Glass-box: explaining AI decisions with counterfactual statements through conversation with a voice-enabled virtual assistant. In: IJCAI, pp. 5868–5870 (2018)Google Scholar