Summary of Temporal Fairness in Decision Making Problems, by Manuel R. Torres et al.
Temporal Fairness in Decision Making Problems
by Manuel R. Torres, Parisa Zehtabi, Michael Cashmore, Daniele Magazzeni, Manuela Veloso
First submitted to arxiv on: 23 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 reimagines fairness in decision-making by considering the long-term consequences of past decisions. The authors propose three novel approaches to optimize for fairness, taking into account the history of previous choices. These methods are tested on four different domains and compared to a baseline approach that ignores temporal fairness. The study highlights the importance of considering the timeline when evaluating fairness in decision-making processes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Decision-makers need to consider how their past decisions affect future outcomes. This paper introduces “temporal fairness,” which looks at the fairness of a series of past decisions. The authors suggest three new ways to optimize for fairness, taking into account this history. They test these approaches on four different areas and compare them to an approach that doesn’t consider temporal fairness. |
