Explaining machine learning classifiers through diverse counterfactual explanations

@article{Mothilal2020ExplainingML,
  title={Explaining machine learning classifiers through diverse counterfactual explanations},
  author={R. K. Mothilal and Amit Sharma and Chenhao Tan},
  journal={Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency},
  year={2020}
}
  • R. K. Mothilal, Amit Sharma, Chenhao Tan
  • Published 2020
  • Computer Science, Mathematics
  • Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency
  • Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose… CONTINUE READING
    73 Citations
    DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models
    • 2
    • Highly Influenced
    • PDF
    Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
    • 18
    • PDF
    Multi-Objective Counterfactual Explanations
    • 8
    • PDF
    Model extraction from counterfactual explanations
    • 1
    • PDF
    Counterfactual Explanations for Machine Learning: A Review
    • 1
    • Highly Influenced
    • PDF
    Algorithmic Recourse: from Counterfactual Explanations to Interventions
    • 18
    • PDF
    GeCo: Quality Counterfactual Explanations in Real Time
    • PDF
    Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)
    • 6
    • Highly Influenced
    • PDF

    References

    SHOWING 1-2 OF 2 REFERENCES
    Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR
    • 444
    • Highly Influential
    • PDF
    "Why Should I Trust You?": Explaining the Predictions of Any Classifier
    • 3,849
    • Highly Influential
    • PDF