Measurable Counterfactual Local Explanations for Any Classifier

@inproceedings{White2020MeasurableCL,
  title={Measurable Counterfactual Local Explanations for Any Classifier},
  author={Adam White and A. Garcez},
  booktitle={ECAI},
  year={2020}
}
  • Adam White, A. Garcez
  • Published in ECAI 2020
  • Computer Science
  • 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Multi-Objective Counterfactual Explanations
    2
    EMAP: Explanation by Minimal Adversarial Perturbation
    Auditing and Debugging Deep Learning Models via Decision Boundaries: Individual-level and Group-level Analysis
    Counterfactual explanation of machine learning survival models
    SurvLIME-Inf: A simplified modification of SurvLIME for explanation of machine learning survival models
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 26 REFERENCES
    "Why Should I Trust You?": Explaining the Predictions of Any Classifier
    3073
    Explaining Explanations in AI
    98
    Contrastive Explanation: A Structural-Model Approach
    25
    Local Rule-Based Explanations of Black Box Decision Systems
    75
    A Unified Approach to Interpreting Model Predictions
    1265
    Explanation in Artificial Intelligence: Insights from the Social Sciences
    638
    Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR
    339
    Anchors: High-Precision Model-Agnostic Explanations
    372
    Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks
    41
    Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review
    105