A General Framework for Fair Regression.

Jack Fitzsimons,Michael Osborne,AbdulRahman Al Ali,Stephen Roberts

doi:10.3390/e21080741

Jack Fitzsimons, Michael Osborne + Show 2 more

Open Access

https://doi.org/10.3390/e21080741

Copy DOI

Journal: Entropy	Publication Date: Jul 29, 2019
Citations: 35	License type: CC BY 4.0

Affiliation: University of Oxford, University of Northampton

Abstract

Fairness, through its many forms and definitions, has become an important issue facing the machine learning community. In this work, we consider how to incorporate group fairness constraints into kernel regression methods, applicable to Gaussian processes, support vector machines, neural network regression and decision tree regression. Further, we focus on examining the effect of incorporating these constraints in decision tree regression, with direct applications to random forests and boosted trees amongst other widespread popular inference techniques. We show that the order of complexity of memory and computation is preserved for such models and tightly binds the expected perturbations to the model in terms of the number of leaves of the trees. Importantly, the approach works on trained models and hence can be easily applied to models in current use and group labels are only required on training data.

Highlights

As the proliferation of machine learning and algorithmic decision making continues to grow throughout industry, the net societal impact of them has been studied with more scrutiny
The report feared that algorithmic decisions informed by big data may have harmful biases, further discriminating against disadvantaged groups
This along with other similar findings has led to a surge in research around algorithmic fairness and the removal of bias from big data

Summary

Introduction

As the proliferation of machine learning and algorithmic decision making continues to grow throughout industry, the net societal impact of them has been studied with more scrutiny. In the USA under the Obama administration, a report on big data collection and analysis found that “big data technologies can cause societal harms beyond damages to privacy” [1]. The report feared that algorithmic decisions informed by big data may have harmful biases, further discriminating against disadvantaged groups. This along with other similar findings has led to a surge in research around algorithmic fairness and the removal of bias from big data. This work is concerned with group fairness under the following definitions as taken from [2]

Objectives

Methods

Conclusion