FairSight: Visual Analytics for Fairness in Decision Making

Abstract

Data-driven decision making related to individuals has become increasingly pervasive, but the issue concerning the potential discrimination has been raised by recent studies. In response, researchers have made efforts to propose and implement fairness measures and algorithms, but those efforts have not been translated to the real-world practice of data-driven decision making. As such, there is still an urgent need to create a viable tool to facilitate fair decision making. We propose FairSight, a visual analytic system to address this need; it is designed to achieve different notions of fairness in ranking decisions through identifying the required actions -- understanding, measuring, diagnosing and mitigating biases -- that together lead to fairer decision making. Through a case study and user study, we demonstrate that the proposed visual analytic and diagnostic modules in the system are effective in understanding the fairness-aware decision pipeline and obtaining more fair outcomes.

arXiv comment10 pages, 8 figures, IEEE VIS (VAST) 2019

References in corpus (15)

• Predictive learning via rule ensembles
• All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
• Counterfactual Fairness
• Improving fairness in machine learning systems: What do industry practitioners need?
• Fairness of Exposure in Rankings
• FA*IR: A Fair Top-k Ranking Algorithm
• On the (im)possibility of fairness
• Distilling a Neural Network Into a Soft Decision Tree
• Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
• Designing Fair Ranking Schemes
• A Nutritional Label for Rankings
• Learning Certifiably Optimal Rule Lists for Categorical Data
• A survey on measuring indirect discrimination in machine learning
• The Doctor Just Won't Accept That!
• Bias In, Bias Out? Evaluating the Folk Wisdom

Cited by in corpus (26)

• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations
• Seeing Like a Toolkit: How Toolkits Envision the Work of AI Ethics
• Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
• Discovering and Validating AI Errors With Crowdsourced Failure Reports
• Visual Analysis of Discrimination in Machine Learning
• Symphony: Composing Interactive Interfaces for Machine Learning
• A Critical Survey on Fairness Benefits of Explainable AI
• A survey on datasets for fairness-aware machine learning
• De-biasing "bias" measurement
• From Information to Choice: A Critical Inquiry Into Visualization Tools for Decision Making
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
• My Model is Unfair, Do People Even Care? Visual Design Affects Trust and Perceived Bias in Machine Learning
• The "Who", "What", and "How" of Responsible AI Governance: A Systematic Review and Meta-Analysis of (Actor, Stage)-Specific Tools
• A Survey of Visual Analytics Techniques for Machine Learning
• The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
• How to be fair? A study of label and selection bias
• DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models
• Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
• M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
• Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
• Help or Hinder? Evaluating the Impact of Fairness Metrics and Algorithms in Visualizations for Consensus Ranking
• A Visual Analytics Framework for Explaining and Diagnosing Transfer Learning Processes
• Trinary Tools for Continuously Valued Binary Classifiers
• Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation
• A Sociotechnical View of Algorithmic Fairness