Summary of Federated Fairness Without Access to Sensitive Groups, by Afroditi Papadaki et al.
Federated Fairness without Access to Sensitive Groups
by Afroditi Papadaki, Natalia Martinez, Martin Bertran, Guillermo Sapiro, Miguel Rodrigues
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Distributed, Parallel, and Cluster Computing (cs.DC)
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 machine learning approach is proposed for guaranteeing group fairness in federated learning without relying on predefined sensitive groups or additional labels. The method allows for trade-offs between fairness and utility, subject to a group size constraint, ensuring that any sufficiently large subset of the population receives at least a minimum level of utility performance from the model. This approach encompasses existing methods as special cases and provides an algorithm with convergence and excess risk guarantees. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers developed a new way to make sure machine learning models are fair to different groups of people without knowing who is in each group ahead of time. The method lets you balance fairness and usefulness, making sure most people get at least some benefits from the model. This approach is useful because it can be used with many types of data and can help make sure everyone gets a good outcome. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
