Summary of Noise-aware Algorithm For Heterogeneous Differentially Private Federated Learning, by Saber Malekmohammadi et al.
Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning
by Saber Malekmohammadi, Yaoliang Yu, Yang Cao
First submitted to arxiv on: 5 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); 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 The proposed Robust-HDP system addresses challenges in federated learning (FL) by efficiently estimating true noise levels in client model updates, reducing noise-levels in aggregated updates, and improving utility and convergence speed while ensuring data privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a world where data is distributed among clients, it’s crucial to achieve high utility and rigorous data privacy. Federated learning (FL) aims to do just that by learning from distributed data. However, existing methods either assume uniform client privacy requirements or don’t work when the server isn’t trusted. Additionally, varying batch sizes and dataset sizes can cause extra noise in model updates. To overcome these challenges, we introduce Robust-HDP, which estimates true noise levels and reduces aggregation noise. This results in better utility and speed while keeping clients’ data private. |
Keywords
» Artificial intelligence » Federated learning
