Summary of A Multivocal Literature Review on Privacy and Fairness in Federated Learning, by Beatrice Balbierer et al.
A Multivocal Literature Review on Privacy and Fairness in Federated Learning
by Beatrice Balbierer, Lukas Heinlein, Domenique Zipperling, Niklas Kühl
First submitted to arxiv on: 16 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 novel approach in Federated Learning aims to decentralize AI training by eliminating data sharing requirements. However, recent studies indicate that sensitive information can still be extracted during this process, emphasizing the importance of implementing differential privacy measures. To ensure real-world applications meet fairness standards, ranging from performance distribution to non-discriminatory behavior, is crucial. In high-risk domains like healthcare, avoiding past discriminatory errors is vital. The literature review highlights a neglected relationship between privacy and fairness in Federated Learning, posing a critical risk for practical applications. Our analysis advocates for the development of integrated frameworks that balance privacy, fairness, and performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Learning is a new way to make artificial intelligence (AI) work without sharing data. But some research shows that even with this approach, personal information can still be found out during training. To make sure AI applications are fair, we need to consider things like equal distribution of results and not being biased against certain groups. In important areas like healthcare, it’s especially important to avoid repeating past mistakes. The study looks at how privacy and fairness fit together in Federated Learning and finds that this connection has been overlooked, which could cause problems for real-world uses. |
Keywords
» Artificial intelligence » Federated learning
