Decomposing Causality and FairnessDownload PDF

01 Mar 2023 (modified: 01 Jun 2023)Submitted to Tiny Papers @ ICLR 2023Readers: Everyone
Keywords: Causality, Fairness
Abstract: It is often informative to decompose key quantities of interest into smaller components, in order to develop a better understanding of the key quantity. In this paper, we focus causality and fairness, where bias attribution can be particularly useful. We show how quantities can be broken down based on independence, or conditional independence criteria, and show how such a decomposition can be used as a diagnosis tool.
5 Replies