Summary of The Intersectionality Problem For Algorithmic Fairness, by Johannes Himmelreich and Arbie Hsu and Kristian Lum and Ellen Veomett
The Intersectionality Problem for Algorithmic Fairness
by Johannes Himmelreich, Arbie Hsu, Kristian Lum, Ellen Veomett
First submitted to arxiv on: 4 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper tackles the challenge of achieving algorithmic fairness across multiple groups, known as intersectionality. The authors highlight the difficulties in verifying whether a model is fair due to the small size of intersectional groups and the need for both statistical and moral-methodological approaches. To address this issue, the paper proposes desiderata to guide the search for solutions and sketches a simple hypothesis testing approach. The proposal is evaluated against these desiderata. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at making sure AI models are fair not just to one group, but to multiple groups at once. This is called intersectionality. It’s hard to check if a model is fair because the groups that overlap between categories are usually small. The authors want to make it easier to find solutions by setting goals and testing ideas. |
