Summary of Flue: Federated Learning with Un-encrypted Model Weights, by Elie Atallah
FLUE: Federated Learning with Un-Encrypted model weights
by Elie Atallah
First submitted to arxiv on: 26 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 In this paper, researchers propose a novel federated learning algorithm that leverages coded local gradients without encryption, exchanging coded proxies for model parameters, and injecting surplus noise to enhance privacy. The algorithm is designed to enable diverse devices to collaboratively train a shared model while keeping training data locally stored, avoiding the need for centralized cloud storage. Two algorithm variants are presented, showcasing convergence and learning rates adaptable to coding schemes and raw data characteristics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This federated learning approach allows devices to share knowledge without sharing private data. The researchers introduce an innovative method that uses coded local gradients, which helps protect sensitive information. By exchanging coded proxies for model parameters and injecting noise, the algorithm provides a robust solution for collaborative learning. The authors also provide simulation results demonstrating promising performance from both federated optimization and machine learning perspectives. |
Keywords
* Artificial intelligence * Federated learning * Machine learning * Optimization
