Fairlearn: Assessing and Improving Fairness of AI Systems
arXiv:2303.16626
Abstract
Fairlearn is an open source project to help practitioners assess and improve fairness of artificial intelligence (AI) systems. The associated Python library, also named fairlearn, supports evaluation of a model's output across affected populations and includes several algorithms for mitigating fairness issues. Grounded in the understanding that fairness is a sociotechnical challenge, the project integrates learning resources that aid practitioners in considering a system's broader societal context.
Cited by in corpus (11)
- Adversarial attacks and defenses in explainable artificial intelligence: A survey
- Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
- One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions
- Unlawful Proxy Discrimination: A Framework for Challenging Inherently Discriminatory Algorithms
- A Sequentially Fair Mechanism for Multiple Sensitive Attributes
- LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
- FairComp: Workshop on Fairness and Robustness in Machine Learning for Ubiquitous Computing
- The State of Algorithmic Fairness in Mobile Human-Computer Interaction
- Fairmetrics: An R package for group fairness evaluation
- Positivity-free Policy Learning with Observational Data
- Simulating counterfactuals