Summary of Does Machine Bring in Extra Bias in Learning? Approximating Fairness in Models Promptly, by Yijun Bian et al.
Does Machine Bring in Extra Bias in Learning? Approximating Fairness in Models Promptly
by Yijun Bian, Yujie Luo
First submitted to arxiv on: 15 May 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 A novel approach to evaluating the discrimination level of machine learning (ML) models is presented in this paper, addressing the concern that existing techniques for assessing group and individual fairness are often incompatible. The proposed “harmonic fairness measure via manifolds” (HFM) measures distances between sets from a manifold perspective, providing a more comprehensive understanding of ML model bias. To overcome computational limitations, an approximation algorithm named “Approximation of distance between sets” (ApproxDist) is developed to facilitate accurate estimation of distances. The paper demonstrates the effectiveness and efficiency of HFM and ApproxDist through empirical results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research addresses a growing concern about discrimination in machine learning models, particularly in high-stakes domains. The authors propose a new way to measure fairness by looking at the distance between groups from a special kind of math called manifolds. They also developed an algorithm to make this measurement more efficient and practical. This can help us create more fair and unbiased AI systems. |
Keywords
» Artificial intelligence » Machine learning
