Toward A Logical Theory Of Fairness and Bias

TL;DR

This paper proposes a formal framework for understanding and applying fairness concepts in machine learning, using epistemic logic to better model environmental factors and biases.

Contribution

It introduces a formal reconstruction of fairness definitions within an epistemic setting, enhancing their theoretical grounding and applicability.

Findings

Formalizes fairness notions in the epistemic situation calculus

Provides a unified logical framework for fairness concepts

Enhances understanding of bias propagation in algorithms

Abstract

Fairness in machine learning is of considerable interest in recent years owing to the propensity of algorithms trained on historical data to amplify and perpetuate historical biases. In this paper, we argue for a formal reconstruction of fairness definitions, not so much to replace existing definitions but to ground their application in an epistemic setting and allow for rich environmental modelling. Consequently we look into three notions: fairness through unawareness, demographic parity and counterfactual fairness, and formalise these in the epistemic situation calculus.