Summary of A Survey on Group Fairness in Federated Learning: Challenges, Taxonomy Of Solutions and Directions For Future Research, by Teresa Salazar et al.
A Survey on Group Fairness in Federated Learning: Challenges, Taxonomy of Solutions and Directions for Future Research
by Teresa Salazar, Helder Araújo, Alberto Cano, Pedro Henriques Abreu
First submitted to arxiv on: 4 Oct 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 A comprehensive survey on group fairness in federated learning is presented, addressing the critical challenges and reviewing related works in this rapidly growing area. The authors highlight the importance of achieving equitable outcomes across different groups defined by sensitive attributes, such as race or gender, in a decentralized approach to training machine learning models. With 47 research works dedicated to addressing this issue, the survey creates a novel taxonomy of approaches based on data partitioning, location, and applied strategies. Additionally, it explores broader concerns related to sensitive groups and their intersections. The review covers datasets and applications commonly used in current research and concludes by emphasizing key areas for future research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning helps train AI models without sharing personal data. But how can we make sure these models are fair? Imagine if an AI system decided who gets a loan or a job based on biased information. That’s not right! This paper looks at how to make federated learning fair for all groups, like men and women, or different races. They find 47 other studies that tried to solve this problem and group them into categories. It’s like organizing books on a shelf by topic. The paper also talks about the challenges of making sure AI systems treat everyone fairly, even when they’re very complex. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
