Welfare and Distributional Impacts of Fair Classification

By Lily Hu, Yiling Chen. 2018

28 citations recorded by the source corpus.

Current methodologies in machine learning analyze the effects of various statistical parity notions of fairness primarily in light of their impacts on predictive accuracy and vendor utility loss. In this paper, we propose a new framework for interpreting the effects of fairness criteria by converting the constrained loss minimization problem into a social welfare maximization problem. This translation moves a classifier and its output into utility space where individuals, groups, and society at-large experience different welfare changes due to classification assignments. Under this characterization, predictions and fairness constraints are seen as shaping societal welfare and distribution and revealing individuals' implied welfare weights in society--weights that may then be interpreted through a fairness lens. The social welfare formulation of the fairness problem brings to the fore concerns of distributive justice that have always had a central albeit more implicit role in standard algorithmic fairness approaches.

Subfields: Artificial Intelligence, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

Citations in the corpus

Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions (2018, background): “For a benevolent social planner, this may be justice or some notion of social welfare [58].”
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias (2018, methodology): “The metrics and algorithms in AIF360 may be viewed from the lens of distributive justice (Hu & Chen, 2018), i.e., relating to decisions about who in a society receives which beneﬁts and goods, and clearly do not capture the full scope of fairness in all situations.”
Algorithmic Fairness: Choices, Assumptions, and Definitions (2021, background): “For a benevolent social planner, this may be some notion of justice or social welfare (Hu & Chen 2018b).”