Getting started with Fairlearn
Microsoft’s approach to fairness falls under the broader context of responsible AI where the fairness tenet accompanies characteristic features such as reliability and safety, privacy and security, inclusiveness, and transparency and accountability aspects. Fairlearn recognizes fairness as a sociotechnical problem and provides tools for evaluating fairness issues and mitigating them. It mainly comprises two key components, as follows:
- Metrics that measure how the model negatively impacts different groups and can be used to perform a comparative analysis in terms of various aspects of fairness and accuracy
- Algorithms for mitigating unfairness in various AI tasks and based on different definitions of fairness
The Fairlearn library consists of multiple packages—essentially, the modules for mitigating fairness-related harms in AI systems, including datasets, metrics, postprocessing, preprocessing, reductions, and experimental...
