Masayoshi Mase, Art B. Owen, Benjamin Seiler
arXiv 1 Nov 2019 · Machine Learning · 30 citations (OpenAlex)
arXiv:1911.00467 · PDF · DOI · OpenAlex · Extracted main text
We introduce a variable importance measure to quantify the impact of individual input variables to a black box function. Our measure is based on the Shapley value from cooperative game theory. Many measures of variable importance operate by changing some predictor values with others held fixed, potentially creating unlikely or even logically impossible combinations. Our cohort Shapley measure uses only observed data points. Instead of changing the value of a predictor we include or exclude subjects similar to the target subject on that predictor to form a similarity cohort. Then we apply Shapley value to the cohort averages. We connect variable importance measures from explainable AI to function decompositions from global sensitivity analysis. We introduce a squared cohort Shapley value that splits previously studied Shapley effects over subjects, consistent with a Shapley axiom.
appendix boundary found by appendix_titled_section at “Appendix 1 Approach of \citet{stru:kono:2010}” · 74% 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 | Kumar, I. E., Venkatasubramanian, S., Scheidegger, C., and Friedler, S (2020) Problems with Shapley-value-based explanations as feature importance measures | 1.000 | 6 | 3 | 100% |
| 2 | Sundararajan, M. and Najmi, A (2020) The many Shapley values for model explanation | 0.874 | 7 | 2 | 100% |
| 3 | Lundberg, S. M. and Lee, S.-I (2017) A unified approach to interpreting model predictions | 0.874 | 5 | 2 | 100% |
| 4 | Strumbelj, E. and Kononenko, I (2010) An efficient explanation of individual classifications using game theory | 0.855 | 8 | 4 | 62% |
| 5 | Song, E., Nelson, B. L., and Staum, J (2016) Shapley effects for global sensitivity analysis: Theory and computation | 0.843 | 3 | 3 | 100% |
| 6 | Owen, A. B (2014) Sobol' indices and Shapley value self | 0.644 | 2 | 2 | 100% |
| 7 | Shapley, L. S (1952) A value for n-person games | 0.644 | 2 | 2 | 100% |
| 8 | Kuo, F., Sloan, I., Wasilkowski, G., and Woźniakowski, H (2010) On decompositions of multivariate functions | 0.511 | 2 | 1 | 100% |
| 9 | Sobol', I. M (1969) Multidimensional Quadrature Formulas and Haar Functions | 0.511 | 2 | 1 | 100% |
| 10 | Strumbelj, E. and Kononenko, I (2014) Explaining prediction models and individual predictions with feature contributions | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 27 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Cohort Shapley value for algorithmic fairness | 0.928 | 4 | 3 |
| 2 | Variable importance without impossible data | 0.843 | 3 | 3 |