FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning
This addresses the problem of detecting intersectional bias in ML models for data scientists and the general public, offering a tool to improve fairness, though it is incremental as it builds on existing visual analytics and subgroup discovery methods.
The authors tackled the challenge of discovering biases in machine learning models by developing FairVis, a visual analytics system that helps users audit fairness across demographic subgroups, and demonstrated its effectiveness in identifying biases in real datasets for income prediction and recidivism.
The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit and explicit societal biases into their outputs, disadvantaging certain demographic subgroups. Discovering which biases a machine learning model has introduced is a great challenge, due to the numerous definitions of fairness and the large number of potentially impacted subgroups. We present FairVis, a mixed-initiative visual analytics system that integrates a novel subgroup discovery technique for users to audit the fairness of machine learning models. Through FairVis, users can apply domain knowledge to generate and investigate known subgroups, and explore suggested and similar subgroups. FairVis' coordinated views enable users to explore a high-level overview of subgroup performance and subsequently drill down into detailed investigation of specific subgroups. We show how FairVis helps to discover biases in two real datasets used in predicting income and recidivism. As a visual analytics system devoted to discovering bias in machine learning, FairVis demonstrates how interactive visualization may help data scientists and the general public understand and create more equitable algorithmic systems.