# Visual Identification of Problematic Bias in Large Label Spaces

arXiv: https://arxiv.org/abs/2201.06386 · HTML: https://mlsanity.com/paper/2201.06386/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 62 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 20 of 20)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Women also Snowboard: Overcoming Bias in Captioning Models](https://mlsanity.com/paper/1803.09797/) (2018)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning](https://mlsanity.com/paper/1904.05419/) (2019)
- [Predictive Inequity in Object Detection](https://mlsanity.com/paper/1902.11097/) (2019)
- [FairSight: Visual Analytics for Fairness in Decision Making](https://mlsanity.com/paper/1908.00176/) (2019)
- [A Survey of Visual Analytics Techniques for Machine Learning](https://mlsanity.com/paper/2008.09632/) (2020)
- [DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models](https://mlsanity.com/paper/2008.08353/) (2020)
- [Boxer: Interactive Comparison of Classifier Results](https://mlsanity.com/paper/2004.07964/) (2020)
- [Themis-ml: A Fairness-aware Machine Learning Interface for End-to-end Discrimination Discovery and Mitigation](https://mlsanity.com/paper/1710.06921/) (2017)
- [Measuring Model Biases in the Absence of Ground Truth](https://mlsanity.com/paper/2103.03417/) (2021)
- [Visual Analysis of Discrimination in Machine Learning](https://mlsanity.com/paper/2007.15182/) (2020)
- [Joint Optimization of AI Fairness and Utility: A Human-Centered Approach](https://mlsanity.com/paper/2002.01621/) (2020)
- [Designing Tools for Semi-Automated Detection of Machine Learning Biases: An Interview Study](https://mlsanity.com/paper/2003.07680/) (2020)
- [A Comparison of Radial and Linear Charts for Visualizing Daily Pattern](https://mlsanity.com/paper/1907.13534/) (2019)
- [The Impact of Presentation Style on Human-In-The-Loop Detection of Algorithmic Bias](https://mlsanity.com/paper/2004.12388/) (2020)
- [Comparative Layouts Revisited: Design Space, Guidelines, and Future Directions](https://mlsanity.com/paper/2009.00192/) (2020)

## Abstract (arXiv)

While the need for well-trained, fair ML systems is increasing ever more, measuring fairness for modern models and datasets is becoming increasingly difficult as they grow at an unprecedented pace. One key challenge in scaling common fairness metrics to such models and datasets is the requirement of exhaustive ground truth labeling, which cannot always be done. Indeed, this often rules out the application of traditional analysis metrics and systems. At the same time, ML-fairness assessments cannot be made algorithmically, as fairness is a highly subjective matter. Thus, domain experts need to be able to extract and reason about bias throughout models and datasets to make informed decisions. While visual analysis tools are of great help when investigating potential bias in DL models, none of the existing approaches have been designed for the specific tasks and challenges that arise in large label spaces. Addressing the lack of visualization work in this area, we propose guidelines for designing visualizations for such large label spaces, considering both technical and ethical issues. Our proposed visualization approach can be integrated into classical model and data pipelines, and we provide an implementation of our techniques open-sourced as a TensorBoard plug-in. With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.