Visual Analysis of Discrimination in Machine Learning

Abstract

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or discriminatory? In this paper, we investigate discrimination in machine learning from a visual analytics perspective and propose an interactive visualization tool, DiscriLens, to support a more comprehensive analysis. To reveal detailed information on algorithmic discrimination, DiscriLens identifies a collection of potentially discriminatory itemsets based on causal modeling and classification rules mining. By combining an extended Euler diagram with a matrix-based visualization, we develop a novel set visualization to facilitate the exploration and interpretation of discriminatory itemsets. A user study shows that users can interpret the visually encoded information in DiscriLens quickly and accurately. Use cases demonstrate that DiscriLens provides informative guidance in understanding and reducing algorithmic discrimination.

References in corpus (8)

• Equality of Opportunity in Supervised Learning
• Improving fairness in machine learning systems: What do industry practitioners need?
• Avoiding Discrimination through Causal Reasoning
• FairSight: Visual Analytics for Fairness in Decision Making
• ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning
• Narvis: Authoring Narrative Slideshows for Introducing Data Visualization Designs
• Predictive Multiplicity in Classification
• FairVis: Visual Analytics for Discovering Intersectional Bias in Machine Learning

Cited by in corpus (4)

• From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation
• KNOWNET: Guided Health Information Seeking from LLMs via Knowledge Graph Integration
• My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning
• Online and Customizable Fairness-aware Learning