Improving on Coalitional Prediction Explanation

Machine learning has proven increasingly essential in many fields but a lot obstacles still hinder its use by non-experts. The lack of trust in the results obtained is foremost among them, and has inspired several explanatory approaches in the literature. These approaches provide a great insight on the predictions of a model, but at a cost of a long computation time. In this paper, we aim to further improve the detection of relevant attributes influencing a prediction, on the strength of feature selection methods.

[1]  Panagiotis Papapetrou,et al.  A peek into the black box: exploring classifiers by randomization , 2014, Data Mining and Knowledge Discovery.

[2]  Verónica Bolón-Canedo,et al.  A review of feature selection methods on synthetic data , 2013, Knowledge and Information Systems.

[3]  Erik Strumbelj,et al.  An Efficient Explanation of Individual Classifications using Game Theory , 2010, J. Mach. Learn. Res..

[4]  Huan Liu,et al.  Efficient Feature Selection via Analysis of Relevance and Redundancy , 2004, J. Mach. Learn. Res..

[5]  Luís Torgo,et al.  OpenML: networked science in machine learning , 2014, SKDD.

[6]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[7]  L. Shapley.  A Value for n-person Games , 1988 .

[8]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[9]  Thomas Lengauer,et al.  Permutation importance: a corrected feature importance measure , 2010, Bioinform..

[10]  Chantal Soulé-Dupuy,et al.  Explaining Single Predictions: A Faster Method , 2020, SOFSEM.

[11]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[12]  Yair Zick,et al.  Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems , 2016, 2016 IEEE Symposium on Security and Privacy (SP).

[13]  Alain Rakotomamonjy,et al.  Variable Selection Using SVM-based Criteria , 2003, J. Mach. Learn. Res..

[14]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[15]  Bernd Bischl,et al.  Visualizing the Feature Importance for Black Box Models , 2018, ECML/PKDD.