Abstract
Recently, a method for explaining the model’s decision for an instance was introduced by Robnik-Šikonja and Kononenko. It is a rare example of a model-independent explanation method. In this paper we make a step towards formalization of the model-independent explanation methods by defining the criteria and a testing environment for such methods. We extensively test the aforementioned method and its variations. The results confirm some of the qualities of the original method as well as expose several of its shortcomings. We propose a new method, based on attribute interactions, that overcomes the shortcomings of the original method and serves as a theoretical framework for further work.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Andrews, R., et al.: Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks. Knowledge-Based Systems 8, 373–389 (1995)
Breiman, L.: Random Forests. Machine Learning Journal 42, 5–32 (2001)
Good, I.J.: Probability and the Weighing of Evidence. C. Griffin, London (1950)
Hamel, L.: Grid Visualization of Support Vector Machines with Unsupervised Learning. In: Proceedings of 2006 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, Toronto, Canada, pp. 1–8 (2006)
Jakulin, A.: Machine Learning Based on Attribute Interactions. PhD Thesis. University of Ljubljana, Faculty of Computer and Information Science (2005)
Jakulin, A., et al.: Grid Nomograms for Visualizing Support Vector Machines. In: KDD 2005: Proceeding of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, Chicago, Illinois, USA, pp. 108–117 (2005)
McGill, W.: Multivariate Information Transmission. IEEE Transactions on Information Theory 4, 195–197 (1981)
Mozina, M., et al.: Nomograms for Visualization of Naive Bayesian Classifier. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) PKDD 2004. LNCS (LNAI), vol. 3202, pp. 337–348. Springer, Heidelberg (2004)
Robnik-Šikonja, M., Kononenko, I.: Explaining Classifications for Individual Instances. IEEE TKDE 20(5), 589–600 (2008)
Szafron, D., et al.: Visual Explanation of Evidence in Additive Classifiers. In: Proceedings of Innovative Applications of Artificial Intelligence (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Štrumbelj, E., Kononenko, I. (2008). Towards a Model Independent Method for Explaining Classification for Individual Instances. In: Song, IY., Eder, J., Nguyen, T.M. (eds) Data Warehousing and Knowledge Discovery. DaWaK 2008. Lecture Notes in Computer Science, vol 5182. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85836-2_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-85836-2_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85835-5
Online ISBN: 978-3-540-85836-2
eBook Packages: Computer ScienceComputer Science (R0)