A Geometric Solution to Fair Representations

By Yuzi He, Keith A. Burghardt, Kristina Lerman. 2020

37 citations recorded by the source corpus.

To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While algorithms have been developed to improve fairness, they typically face at least one of three shortcomings: they are not interpretable, their prediction quality deteriorates quickly compared to unbiased equivalents, and %the methodology cannot easily extend other algorithms they are not easily transferable across models% (e.g., methods to reduce bias in random forests cannot be extended to neural networks) . To address these shortcomings, we propose a geometric method that removes correlations between data and any number of protected variables. Further, we can control the strength of debiasing through an adjustable parameter to address the trade-off between prediction quality and fairness. The resulting features are interpretable and can be used with many popular models, such as linear regression, random forest, and multilayer perceptrons. The resulting predictions are found to be more accurate and fair compared to several state-of-the-art fair AI algorithms across a variety of benchmark datasets. Our work shows that debiasing data is a simple and effective solution toward improving fairness.

Subfields: Artificial Intelligence, Safety Research, Representation & Self-Supervised Learning, AI Ethics, Fairness & Society

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

In Representation & Self-Supervised Learning

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, background): “In this work, authors evaluate the performance of their approach on different benchmark datasets, such as COMPAS, Adult and German, and compare them against various different approaches for fair learning algorithms considering fairness and accuracy measures [65, 72, 158, 159].”
Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation (2021, background): “He, Burghardt, and Lerman (2020) minimize correlation between the sensitive attributes and the representations to achieve fairness.”
FairFed: Enabling Group Fairness in Federated Learning (2021, unknown): “This is due to the fact that under homogeneous sampling, the distributions of the local datasets are statistically similar (and reﬂect the original distribution with enough samples), resulting in similar debiasing effect being applied across all clients when us-ing the pre-processing methods (reweig”