Oct 1, 2019 · The goal of this paper is to discuss the application of data management techniques in algorithmic fairness. In Sec 2 we make a distinction ...

Aug 20, 2019 · In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept ...

Dec 18, 2024 · In this paper, we first make a distinction between associational and causal definitions of fairness in the literature and argue that the concept ...

A variable is defined by the function of its direct causes and unknown disturbances. ○ Represented as a Causal DAG G(V,E). ○ A variable (V) has incoming edges ...

Sep 17, 2022 · Progress in fair machine learning and equitable algorithm design hinges on data, which can be appropriately used only if adequately documented.

In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables.

We categorize computational biases into three different types according to the source of bias: data bias, measurement bias, and algorithm bias. We will ...

Aug 14, 2021 · A novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute ...

Data Management for Causal Algorithmic Fairness. IEEE Data Engineering Bulletin 2019. Paper PDF. Babak Salimi, Luke Rodriguez, Bill Howe, Dan Suciu ...

In this paper, we formalize the situation as a database repair problem, proving sufficient conditions for fair classifiers in terms of admissible variables.