arXiv Open Access 2019

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

Samuel Deng Achille Varzi

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CY cs.LG

Penulis (2)

Samuel Deng

Achille Varzi

Format Sitasi

APA MLA BibTeX

Deng, S., Varzi, A. (2019). Methodological Blind Spots in Machine Learning Fairness: Lessons from the Philosophy of Science and Computer Science. https://arxiv.org/abs/1910.14210

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2019
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓