STNANATHMar 21, 2017

On Shapley value for measuring importance of dependent inputs

arXiv:1610.02080182 citationsh-index: 60
AI Analysis

Provides a principled alternative for importance quantification in the presence of dependent inputs, addressing a known limitation of existing methods.

The paper argues that Shapley value avoids conceptual problems of ANOVA-based methods for measuring input importance when variables are dependent, demonstrating with simple examples that yield intuitive closed-form values.

This paper makes the case for using Shapley value to quantify the importance of random input variables to a function. Alternatives based on the ANOVA decomposition can run into conceptual and computational problems when the input variables are dependent. Our main goal here is to show that Shapley value removes the conceptual problems. We do this with some simple examples where Shapley value leads to intuitively reasonable nearly closed form values.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes