Relation-Based Counterfactual Explanations for Bayesian Network Classifiers

We propose a general method for generating counterfactual explanations (CFXs) for a range of Bayesian Network Classifiers (BCs), e.g. singleor multi-label, binary or multidimensional. We focus on explanations built from relations of (critical and potential) influence between variables, indicating the reasons for classifications, rather than any probabilistic information. We show by means of a theoretical analysis of CFXs’ properties that they serve the purpose of indicating (potentially) pivotal factors in the classification process, whose absence would give rise to different classifications. We then prove empirically for various BCs that CFXs provide useful information in real world settings, e.g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature.

[1]  LacaveCarmen,et al.  A review of explanation methods for Bayesian networks , 2002 .

[2]  Bolei Zhou,et al.  Network Dissection: Quantifying Interpretability of Deep Visual Representations , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[4]  Adnan Darwiche,et al.  Compiling Bayesian Network Classifiers into Decision Graphs , 2019, AAAI.

[5]  Adnan Darwiche,et al.  Same-decision probability: A confidence measure for threshold-based decisions , 2012, Int. J. Approx. Reason..

[6]  André Elisseeff,et al.  Explanation Trees for Causal Bayesian Networks , 2008, UAI.

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

[8]  Concha Bielza,et al.  Discrete Bayesian Network Classifiers , 2014, ACM Comput. Surv..

[9]  Tim Miller,et al.  Explanation in Artificial Intelligence: Insights from the Social Sciences , 2017, Artif. Intell..

[10]  T. Lombrozo,et al.  Simplicity and probability in causal explanation , 2007, Cognitive Psychology.

[11]  Christophe Labreuche,et al.  Symbolic and Quantitative Approaches to Reasoning with Uncertainty , 2015, Lecture Notes in Computer Science.

[12]  Philipp Koehn,et al.  Cognitive Psychology , 1992, Ageing and Society.

[13]  Carlos Guestrin,et al.  Anchors: High-Precision Model-Agnostic Explanations , 2018, AAAI.

[14]  Maja Matarić,et al.  On Relevance , 2018, Inclusion as Social Justice.

[15]  Walter Karlen,et al.  CXPlain: Causal Explanations for Model Interpretation under Uncertainty , 2019, NeurIPS.

[16]  共立出版株式会社.  コンピュータ・サイエンス : ACM computing surveys , 1978 .

[17]  Adnan Darwiche,et al.  A Symbolic Approach to Explaining Bayesian Network Classifiers , 2018, IJCAI.

[18]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

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