Summary of Hidden or Inferred: Fair Learning-to-rank with Unknown Demographics, by Oluseun Olulana et al.
Hidden or Inferred: Fair Learning-To-Rank with Unknown Demographics
by Oluseun Olulana, Kathleen Cachel, Fabricio Murai, Elke Rundensteiner
First submitted to arxiv on: 24 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 investigates the impact of errors in demographic inference on the fairness performance of popular fair learning-to-rank (LTR) strategies. It examines a spectrum of fair LTR strategies, ranging from those that use and infer sensitive attributes to those that do not, and assesses their robustness to inference noise. The findings suggest that as inference errors increase, LTR-based methods that incorporate fairness considerations may actually increase bias, whereas fair re-ranking strategies are more resilient. This research has implications for the development of fair ML models in applications with profound life implications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how mistakes in guessing someone’s race or sex affect the fairness of computer programs that rank things. These programs are used to make important decisions about people’s lives. The researchers tested different ways of making these programs more fair, and found that some methods get worse as they try to guess more information. However, other methods that don’t use this guessed information are more reliable. This study is important because it helps us understand how to make computer programs fairer in situations where we can’t always know the right answer. |
Keywords
» Artificial intelligence » Inference
