Summary of One Node Per User: Node-level Federated Learning For Graph Neural Networks, by Zhidong Gao et al.
One Node Per User: Node-Level Federated Learning for Graph Neural Networks
by Zhidong Gao, Yuanxiong Guo, Yanmin Gong
First submitted to arxiv on: 29 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 a novel framework for node-level federated graph learning, addressing privacy concerns in Graph Neural Networks (GNNs) training. Federated learning enables collaborative model training without sharing raw data, but integrating it with GNNs presents unique challenges. The proposed approach decouples the message-passing and feature vector transformation processes of the first GNN layer, allowing them to be executed separately on user devices and a cloud server. Additionally, the paper introduces a graph Laplacian term based on the feature vector’s latent representation to regulate user-side model updates. Experimental results on multiple datasets show that this approach achieves better performance compared with baselines. This paper’s contributions include developing a node-level federated graph learning framework and improving GNNs’ collaborative training capabilities while maintaining users’ privacy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research solves a problem in computer science called Graph Neural Networks (GNNs). When people train these networks, they need to collect lots of data from each person, which can be bad for privacy. To fix this, the researchers came up with a new way to work together on training GNNs without sharing all the data. They separated two parts of the process: one that happens on personal devices and one that happens in the cloud. This helps keep people’s information safe while still improving the accuracy of the networks. |
Keywords
» Artificial intelligence » Federated learning » Gnn
