NICE: An Algorithm for Nearest Instance Counterfactual Explanations

In this paper we suggest NICE: a new algorithm to generate counterfactual explanations for heterogeneous tabular data. The design of our algorithm specifically takes into account algorithmic requirements that often emerge in real-life deployments: the ability to provide an explanation for all predictions, being efficient in run-time, and being able to handle any classification model (also nondifferentiable ones). More specifically, our approach exploits information from a nearest instance to speed up the search process. We propose four versions of NICE, where three of them optimize the explanations for one of the following properties: sparsity, proximity or plausibility. An extensive empirical comparison on 10 datasets shows that our algorithm performs better on all properties than the current state-of-the-art. These analyses show a trade-off between on the one hand plausiblity and on the other hand proximity or sparsity, with our different optimization methods offering the choice to select the preferred trade-off. An open-source implementation of NICE can be found at https://github.com/ADMAntwerp/NICE.

[1]  Hiroki Arimura,et al.  DACE: Distribution-Aware Counterfactual Explanation by Mixed-Integer Linear Optimization , 2020, IJCAI.

[2]  Donald Nute,et al.  Counterfactuals , 1975, Notre Dame J. Formal Log..

[3]  Martin Wattenberg,et al.  The What-If Tool: Interactive Probing of Machine Learning Models , 2019, IEEE Transactions on Visualization and Computer Graphics.

[4]  Foster J. Provost,et al.  Explaining Data-Driven Document Classifications , 2013, MIS Q..

[5]  Amit Sharma,et al.  Explaining machine learning classifiers through diverse counterfactual explanations , 2020, FAT*.

[6]  Peter A. Flach,et al.  Explainability fact sheets: a framework for systematic assessment of explainable approaches , 2019, FAT*.

[7]  John P. Dickerson,et al.  Counterfactual Explanations for Machine Learning: A Review , 2020, ArXiv.

[8]  Jacques Wainer,et al.  Uses of artificial intelligence in the Brazilian customs fraud detection system , 2008, DG.O.

[9]  Amit Dhurandhar,et al.  Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives , 2018, NeurIPS.

[10]  Theodoros Evgeniou,et al.  A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C , 2020, Advances in Data Analysis and Classification.

[11]  Amit Dhurandhar,et al.  Model Agnostic Contrastive Explanations for Structured Data , 2019, ArXiv.

[12]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[13]  Yong Hu,et al.  The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature , 2011, Decis. Support Syst..

[14]  Alison Callahan,et al.  Machine Learning in Healthcare , 2017 .

[15]  Foster Provost,et al.  Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach , 2020, MIS Quarterly.

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

[17]  Solon Barocas,et al.  The hidden assumptions behind counterfactual explanations and principal reasons , 2019, FAT*.

[18]  Boris Kment,et al.  Counterfactuals and Explanation , 2006 .

[19]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[20]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[21]  Randal S. Olson,et al.  PMLB: a large benchmark suite for machine learning evaluation and comparison , 2017, BioData Mining.

[22]  Barry Smyth,et al.  Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI) , 2020, ICCBR.

[23]  Amit Sharma,et al.  Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers , 2019, ArXiv.

[24]  M. Friedman.  A Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings , 1940 .

[25]  David Martens,et al.  Explainable Image Classification with Evidence Counterfactual , 2020, ArXiv.

[26]  Been Kim,et al.  Towards A Rigorous Science of Interpretable Machine Learning , 2017, 1702.08608.

[27]  J. Suykens,et al.  Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research , 2015, Eur. J. Oper. Res..

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

[29]  David Martens,et al.  Value-added tax fraud detection with scalable anomaly detection techniques , 2020, Appl. Soft Comput..

[30]  Gjergji Kasneci,et al.  On Counterfactual Explanations under Predictive Multiplicity , 2020, UAI.

[31]  Tony R. Martinez,et al.  Improved Heterogeneous Distance Functions , 1996, J. Artif. Intell. Res..

[32]  Janis Klaise,et al.  Interpretable Counterfactual Explanations Guided by Prototypes , 2019, ECML/PKDD.

[33]  Bernhard Schölkopf,et al.  A survey of algorithmic recourse: definitions, formulations, solutions, and prospects , 2020, ArXiv.

[34]  Bernd Bischl,et al.  Multi-Objective Counterfactual Explanations , 2020, PPSN.

[35]  Oluwasanmi Koyejo,et al.  Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems , 2019, ArXiv.