%0 Conference Proceedings
%T Automated Machine Learning for Studying the Trade-Off Between Predictive Accuracy and Interpretability
%+ School of Computing [Kent]
%A Freitas, Alex, A.
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Canterbury, United Kingdom
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-11713
%P 48-66
%8 2019-08-26
%D 2019
%R 10.1007/978-3-030-29726-8_4
%K Automated Machine Learning (Auto-ML)
%K Classification algorithms
%K Interpretable models
%Z Computer Science [cs]Conference papers
%X Automated Machine Learning (Auto-ML) methods search for the best classification algorithm and its best hyper-parameter settings for each input dataset. Auto-ML methods normally maximize only predictive accuracy, ignoring the classification model’s interpretability – an important criterion in many applications. Hence, we propose a novel approach, based on Auto-ML, to investigate the trade-off between the predictive accuracy and the interpretability of classification-model representations. The experiments used the Auto-WEKA tool to investigate this trade-off. We distinguish between white box (interpretable) model representations and two other types of model representations: black box (non-interpretable) and grey box (partly interpretable). We consider as white box the models based on the following 6 interpretable knowledge representations: decision trees, If-Then classification rules, decision tables, Bayesian network classifiers, nearest neighbours and logistic regression. The experiments used 16 datasets and two runtime limits per Auto-WEKA run: 5 h and 20 h. Overall, the best white box model was more accurate than the best non-white box model in 4 of the 16 datasets in the 5-hour runs, and in 7 of the 16 datasets in the 20-hour runs. However, the predictive accuracy differences between the best white box and best non-white box models were often very small. If we accept a predictive accuracy loss of 1% in order to benefit from the interpretability of a white box model representation, we would prefer the best white box model in 8 of the 16 datasets in the 5-hour runs, and in 10 of the 16 datasets in the 20-hour runs.
%G English
%Z TC 5
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-02520064/document
%2 https://inria.hal.science/hal-02520064/file/485369_1_En_4_Chapter.pdf
%L hal-02520064
%U https://inria.hal.science/hal-02520064
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-11713