Methodological Blind Spots in Machine Learning Fairness: Lessons from the Philosophy of Science and Computer Science

TL;DR

This paper critically examines foundational assumptions in ML fairness using philosophy of science and computer science concepts, highlighting methodological blind spots and advocating for interdisciplinary approaches.

Contribution

It introduces philosophical perspectives to identify and analyze blind spots in ML fairness methodologies, promoting more rigorous and reflective research practices.

Findings

Identifies abstraction, induction, and measurement as key blind spots.

Highlights the need for interdisciplinary approaches in fair-ML research.

Encourages critical evaluation of foundational assumptions in ML fairness.

Abstract

In the ML fairness literature, there have been few investigations through the viewpoint of philosophy, a lens that encourages the critical evaluation of basic assumptions. The purpose of this paper is to use three ideas from the philosophy of science and computer science to tease out blind spots in the assumptions that underlie ML fairness: abstraction, induction, and measurement. Through this investigation, we hope to warn of these methodological blind spots and encourage further interdisciplinary investigation in fair-ML through the framework of philosophy.