Generating Counterfactual and Contrastive Explanations using SHAP

With the advent of GDPR, the domain of explainable AI and model interpretability has gained added impetus. Methods to extract and communicate visibility into decision-making models have become legal requirement. Two specific types of explanations, contrastive and counterfactual have been identified as suitable for human understanding. In this paper, we propose a model agnostic method and its systemic implementation to generate these explanations using shapely additive explanations (SHAP). We discuss a generative pipeline to create contrastive explanations and use it to further to generate counterfactual datapoints. This pipeline is tested and discussed on the IRIS, Wine Quality & Mobile Features dataset. Analysis of the results obtained follows.

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

[2]  M. I. V. Eale,et al.  SLAVE TO THE ALGORITHM ? WHY A ‘ RIGHT TO AN EXPLANATION ’ IS PROBABLY NOT THE REMEDY YOU ARE LOOKING FOR , 2017 .

[3]  Brandon M. Greenwell,et al.  Interpretable Machine Learning , 2019, Hands-On Machine Learning with R.

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

[5]  Mark A. Neerincx,et al.  Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences , 2018, IJCAI 2018.

[6]  Davide Castelvecchi,et al.  Can we open the black box of AI? , 2016, Nature.

[7]  김기경.  Accountability , 2019, Encyclopedia of Food and Agricultural Ethics.

[8]  M. J. Robeer,et al.  Contrastive Explanation for Machine Learning , 2018 .

[9]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.

[10]  Peter A. Flach,et al.  Conversational Explanations of Machine Learning Predictions Through Class-contrastive Counterfactual Statements , 2018, IJCAI.

[11]  Chris Russell,et al.  Explaining Explanations in AI , 2018, FAT.

[12]  Erik Weber,et al.  Remote causes, bad explanations? , 2002 .

[13]  Trevor Darrell,et al.  Generating Counterfactual Explanations with Natural Language , 2018, ICML 2018.

[14]  Mark A. Neerincx,et al.  Contrastive Explanations with Local Foil Trees , 2018, ICML 2018.

[15]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[16]  Zachary Chase Lipton.  The mythos of model interpretability , 2016, ACM Queue.