Counterfactual Explanations for Machine Learning: Challenges Revisited

Abstract

Counterfactual explanations (CFEs) are an emerging technique under the umbrella of interpretability of machine learning (ML) models. They provide ``what if'' feedback of the form ``if an input datapoint were $x^{\prime }$ instead of $x$, then an ML model's output would be $y^{\prime }$ instead of $y$.'' Counterfactual explainability for ML models has yet to see widespread adoption in industry. In this short paper, we posit reasons for this slow uptake. Leveraging recent work outlining desirable properties of CFEs and our experience running the ML wing of a model monitoring startup, we identify outstanding obstacles hindering CFE deployment in industry.

arXiv commentPresented at CHI HCXAI 2021 workshop

References in corpus (10)

• A Survey of Learning Causality with Data: Problems and Methods
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• Ethical Dimensions of Visualization Research
• Runaway Feedback Loops in Predictive Policing
• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
• Model-Agnostic Counterfactual Explanations for Consequential Decisions
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• Measuring Non-Expert Comprehension of Machine Learning Fairness Metrics