30 citations · 35 across the 3 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 3 cited
Cohort Shapley value for algorithmic fairness
Masayoshi Mase, Art B. Owen, Benjamin B. Seiler
Cohort Shapley value is a model-free method of variable importance grounded in game theory that does not use any unobserved and potentially impossible feature combinations. We use…
stat.AP2021
What makes you unique?
Benjamin B. Seiler, Masayoshi Mase, Art B. Owen
This paper proposes a uniqueness Shapley measure to compare the extent to which different variables are able to identify a subject. Revealing the value of a variable on subject …