Summary of Long-term Fairness Inquiries and Pursuits in Machine Learning: a Survey Of Notions, Methods, and Challenges, by Usman Gohar et al.
Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges
by Usman Gohar, Zeyu Tang, Jialu Wang, Kun Zhang, Peter L. Spirtes, Yang Liu, Lu Cheng
First submitted to arxiv on: 10 Jun 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 This paper addresses the pressing concern of fairness in Machine Learning systems, particularly in high-stakes domains. Recent studies have shown that off-the-shelf fairness approaches may not be sufficient to achieve long-term fairness due to the introduction of feedback loops and interactions between models and their environment. The authors review existing literature on long-term fairness from different perspectives, present a taxonomy for long-term fairness studies, highlight key challenges, and outline future research directions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making sure that machines are fair when they make decisions. Right now, machines are used to make important decisions, but some people are worried that these decisions might not be fair. The authors looked at what others have said about this problem and came up with a way to organize all the different ideas about fairness. They also talked about what’s hard about making sure machines are fair and where we should go from here. |
Keywords
» Artificial intelligence » Machine learning
