Masayoshi Mase, Art B. Owen, Benjamin B. Seiler
arXiv 31 May 2022 · Machine Learning · publishedAnnual Review of Statistics and Its Application (2023) · 7 citations (OpenAlex)
arXiv:2205.15750 · PDF · DOI · OpenAlex · Extracted main text
The most popular methods for measuring importance of the variables in a black box prediction algorithm make use of synthetic inputs that combine predictor variables from multiple subjects. These inputs can be unlikely, physically impossible, or even logically impossible. As a result, the predictions for such cases can be based on data very unlike any the black box was trained on. We think that users cannot trust an explanation of the decision of a prediction algorithm when the explanation uses such values. Instead we advocate a method called Cohort Shapley that is grounded in economic game theory and unlike most other game theoretic methods, it uses only actually observed data to quantify variable importance. Cohort Shapley works by narrowing the cohort of subjects judged to be similar to a target subject on one or more features. We illustrate it on an algorithmic fairness problem where it is essential to attribute importance to protected variables that the model was not trained on.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Molnar, C (2018) Interpretable machine learning: A Guide for Making Black Box Models Explainable | 0.928 | 4 | 3 | 100% |
| 2 | Sundararajan, M. and Najmi, A (2020) The many Shapley values for model explanation | 0.928 | 4 | 3 | 100% |
| 3 | Angwin, J., Larson, J., Mattu, S., and Kirchner, L (2016) Machine bias: there’s software used across the country to predict future criminals. and it’s biased against blacks | 0.874 | 11 | 2 | 100% |
| 4 | Lundberg, S. M. and Lee, S.-I (2017) A unified approach to interpreting model predictions | 0.843 | 3 | 3 | 100% |
| 5 | Mase, M., Owen, A. B., and Seiler, B. B (2019) Explaining black box decisions by Shapley cohort refinement self | 0.843 | 3 | 3 | 100% |
| 6 | Ribeiro, M. T., Singh, S., and Guestrin, C (2016) Why should I trust you?: Explaining the predictions of any classifier | 0.843 | 3 | 3 | 100% |
| 7 | Kumar, I. E., Venkatasubramanian, S., Scheidegger, C., and Friedler, S (2020) Problems with Shapley-value-based explanations as feature importance measures | 0.811 | 4 | 2 | 100% |
| 8 | Owen, A. B. and Prieur, C (2017) On Shapley value for measuring importance of dependent inputs self | 0.737 | 3 | 2 | 100% |
| 9 | Breiman, L (2001) Random forests | 0.644 | 2 | 2 | 100% |
| 10 | Chastaing, G., Gamboa, F., and Prieur, C (2012) Generalized Hoeffding-Sobol' decomposition for dependent variables-application to sensitivity analysis | 0.644 | 2 | 2 | 100% |
Showing the top 10 of 84 scored citations.