Visual Identification of Problematic Bias in Large Label Spaces

TL;DR

This paper introduces a visualization approach and guidelines for identifying bias in large label space models, enabling fairness assessment without exhaustive ground truth labeling.

Contribution

It presents a novel visualization method and design guidelines specifically tailored for large label spaces, integrated into TensorBoard for bias analysis.

Findings

Facilitates bias detection in large label datasets visually.

Supports comparison of different models and datasets.

Addresses technical and ethical considerations in visualization design.

Abstract

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.