Summary of Privacy-preserving Gradient-based Fair Federated Learning, by Janis Adamek et al.
Privacy-preserving gradient-based fair federated learning
by Janis Adamek, Moritz Schulze Darup
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Systems and Control (eess.SY)
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 |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine if multiple people could work together to train a computer model without sharing their personal data. That’s essentially what federated learning (FL) does. The challenge is making sure everyone gets a fair chance to contribute, while also keeping their data private. Some previous solutions have focused on either fairness or privacy, but not both. Our research presents a new approach that combines these two goals. We use homomorphic encryption, which allows us to process the data locally without sharing it with anyone else. This makes our method more practical and opens up possibilities for using FL in areas like control systems. |
Keywords
» Artificial intelligence » Federated learning
