Summary of Hifgl: a Hierarchical Framework For Cross-silo Cross-device Federated Graph Learning, by Zhuoning Guo et al.
HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning
by Zhuoning Guo, Duanyi Yao, Qiang Yang, Hao Liu
First submitted to arxiv on: 15 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: 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 In this paper, researchers propose a Hierarchical Federated Graph Learning (HiFGL) framework to learn high-quality representations from distributed graph data while preserving privacy. The framework addresses the challenging task of cross-silo cross-device federated learning by safeguarding GNN training on heterogeneous clients and ensuring graph integrity. To achieve multi-level privacy preservation, the authors introduce a Secret Message Passing (SecMP) scheme that shields sensitive information at subgraph and node levels. Experimental results on real-world datasets demonstrate the superiority of HiFGL compared to several baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Graph Learning helps learn from distributed graph data while keeping it private. A new way called Hierarchical Federated Graph Learning (HiFGL) makes it easier to do this when there are many different devices and clients involved. HiFGL is like a shield that protects sensitive information in the graphs, making sure only authorized people can access it. The researchers tested this idea with real-world data and showed that it works better than other methods. |
Keywords
* Artificial intelligence * Federated learning * Gnn
