FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning

04/10/2019
by   Ángel Alexander Cabrera, et al.
0

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 in understanding and creating more equitable algorithmic systems.

READ FULL TEXT
research
02/04/2017

Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective

Interactive model analysis, the process of understanding, diagnosing, an...
research
09/27/2018

Visual Analytics for Automated Model Discovery

A recent advancement in the machine learning community is the developmen...
research
07/30/2020

Visual Analysis of Discrimination in Machine Learning

The growing use of automated decision-making in critical applications, s...
research
09/14/2022

RMExplorer: A Visual Analytics Approach to Explore the Performance and the Fairness of Disease Risk Models on Population Subgroups

Disease risk models can identify high-risk patients and help clinicians ...
research
07/16/2021

A Survey on Bias in Visual Datasets

Computer Vision (CV) has achieved remarkable results, outperforming huma...
research
03/27/2023

Uncovering Bias in Personal Informatics

Personal informatics (PI) systems, powered by smartphones and wearables,...
research
11/19/2020

Toward a Bias-Aware Future for Mixed-Initiative Visual Analytics

Mixed-initiative visual analytics systems incorporate well-established d...

Please sign up or login with your details

Forgot password? Click here to reset