# FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning

arXiv: https://arxiv.org/abs/1904.05419 · HTML: https://mlsanity.com/paper/1904.05419/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2019.

## Built on by (most cited first, 30 of 93)

- [Robustness Gym: Unifying the NLP Evaluation Landscape](https://mlsanity.com/paper/2101.04840/) (2021)
- [The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models](https://mlsanity.com/paper/2107.00758/) (2021)
- [A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges](https://mlsanity.com/paper/2305.06969/) (2023)
- [Representation Bias in Data: A Survey on Identification and Resolution Techniques](https://mlsanity.com/paper/2203.11852/) (2022)
- [Improving Human-AI Collaboration With Descriptions of AI Behavior](https://mlsanity.com/paper/2301.06937/) (2023)
- [Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits](https://mlsanity.com/paper/2205.06922/) (2022)
- [Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data](https://mlsanity.com/paper/2310.16524/) (2023)
- [A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms](https://mlsanity.com/paper/2206.14983/) (2022)
- [M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis](https://mlsanity.com/paper/2107.08264/) (2021)
- [The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations](https://mlsanity.com/paper/2212.11737/) (2022)
- [Discovering and Validating AI Errors With Crowdsourced Failure Reports](https://mlsanity.com/paper/2109.11690/) (2021)
- [Farsight: Fostering Responsible AI Awareness During AI Application Prototyping](https://mlsanity.com/paper/2402.15350/) (2024)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness](https://mlsanity.com/paper/2303.17555/) (2023)
- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models](https://mlsanity.com/paper/2110.15499/) (2021)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [De-biasing "bias" measurement](https://mlsanity.com/paper/2205.05770/) (2022)
- [Symphony: Composing Interactive Interfaces for Machine Learning](https://mlsanity.com/paper/2202.08946/) (2022)
- [D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias](https://mlsanity.com/paper/2208.05126/) (2022)
- [LMdiff: A Visual Diff Tool to Compare Language Models](https://mlsanity.com/paper/2111.01582/) (2021)
- [Investigating Practices and Opportunities for Cross-functional Collaboration around AI Fairness in Industry Practice](https://mlsanity.com/paper/2306.06542/) (2023)
- [Towards Involving End-users in Interactive Human-in-the-loop AI Fairness](https://mlsanity.com/paper/2204.10464/) (2022)
- [DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps](https://mlsanity.com/paper/2205.06935/) (2022)
- [Angler: Helping Machine Translation Practitioners Prioritize Model Improvements](https://mlsanity.com/paper/2304.05967/) (2023)
- [How to be fair? A study of label and selection bias](https://mlsanity.com/paper/2403.14282/) (2024)
- [Auditing of AI: Legal, Ethical and Technical Approaches](https://mlsanity.com/paper/2407.06235/) (2024)
- [Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness](https://mlsanity.com/paper/2206.00474/) (2022)
- [WordBias: An Interactive Visual Tool for Discovering Intersectional Biases Encoded in Word Embeddings](https://mlsanity.com/paper/2103.03598/) (2021)
- [VisCUIT: Visual Auditor for Bias in CNN Image Classifier](https://mlsanity.com/paper/2204.05899/) (2022)

## Abstract (arXiv)

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.