Summary of Differentially-private Multi-tier Federated Learning, by Evan Chen et al.
Differentially-Private Multi-Tier Federated Learning
by Evan Chen, Frank Po-Chen Lin, Dong-Jun Han, Christopher G. Brinton
First submitted to arxiv on: 21 Jan 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 This paper proposes Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M^2FDP), an enhanced federated learning methodology for optimizing privacy and performance in hierarchical networks. The approach extends Hierarchical Differential Privacy (HDP) to Multi-Tier Differential Privacy (MDP), injecting noise into model parameters at different layers of the network, depending on trust models within subnetworks. The authors analyze the convergence behavior of M^2FDP, identifying conditions for sublinear training process convergence, which depends on network hierarchy, trust model, and target privacy level. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep personal data safe when machines learn together without sharing their information directly. It creates a new way to do this called Multi-Tier Federated Learning with Multi-Tier Differential Privacy (M^2FDP). This method makes sure that the information shared is private, and it does this by adding noise to the information at different levels of a network. The researchers tested how well this method works and found out when it will work quickly and efficiently. |
Keywords
* Artificial intelligence * Federated learning
