Measurable Counterfactual Local Explanations for Any Classifier
arXiv:1908.03020
Abstract
We propose a novel method for explaining the predictions of any classifier. In our approach, local explanations are expected to explain both the outcome of a prediction and how that prediction would change if 'things had been different'. Furthermore, we argue that satisfactory explanations cannot be dissociated from a notion and measure of fidelity, as advocated in the early days of neural networks' knowledge extraction. We introduce a definition of fidelity to the underlying classifier for local explanation models which is based on distances to a target decision boundary. A system called CLEAR: Counterfactual Local Explanations via Regression, is introduced and evaluated. CLEAR generates w-counterfactual explanations that state minimum changes necessary to flip a prediction's classification. CLEAR then builds local regression models, using the w-counterfactuals to measure and improve the fidelity of its regressions. By contrast, the popular LIME method, which also uses regression to generate local explanations, neither measures its own fidelity nor generates counterfactuals. CLEAR's regressions are found to have significantly higher fidelity than LIME's, averaging over 45% higher in this paper's four case studies.
References in corpus (2)
Cited by in corpus (14)
- Counterfactual Shapley Additive Explanations
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data
- Model-Based Counterfactual Synthesizer for Interpretation
- Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting
- An exact counterfactual-example-based approach to tree-ensemble models interpretability
- Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation
- SurvLIME-Inf: A simplified modification of SurvLIME for explanation of machine learning survival models
- EMAP: Explanation by Minimal Adversarial Perturbation
- Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
- Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning
- Harnessing value from data science in business: ensuring explainability and fairness of solutions
- On Predictive Explanation of Data Anomalies
- Influence-Driven Explanations for Bayesian Network Classifiers