Summary of Long-term Fair Decision Making Through Deep Generative Models, by Yaowei Hu et al.
Long-Term Fair Decision Making through Deep Generative Models
by Yaowei Hu, Yongkai Wu, Lu Zhang
First submitted to arxiv on: 20 Jan 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 This paper presents a novel approach to mitigating group disparity in sequential decision-making systems over the long term, a problem known as long-term fair machine learning. To quantify this fairness, the authors employ the 1-Wasserstein distance between interventional distributions of different demographic groups at a large time step. A three-phase learning framework is proposed, where a deep generative model generates high-fidelity data for training a decision model using performative risk minimization and repeated gradient descent. The efficacy of this method is demonstrated through empirical evaluation on both synthetic and semi-synthetic datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make sure that important decisions made over time are fair and equal for everyone, even if the people making those decisions don’t always have all the information. To measure fairness, scientists use a special tool called the 1-Wasserstein distance. The researchers developed a new way to learn and make decisions using a combination of machine learning and deep generative models. They tested this approach on fake and real data sets and showed that it works well. |
Keywords
* Artificial intelligence * Generative model * Gradient descent * Machine learning
