One Node Per User: Node-Level Federated Learning for Graph Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910624301187072 |
|---|---|
| author | Gao, Zhidong Guo, Yuanxiong Gong, Yanmin |
| author_facet | Gao, Zhidong Guo, Yuanxiong Gong, Yanmin |
| contents | Graph Neural Networks (GNNs) training often necessitates gathering raw user data on a central server, which raises significant privacy concerns. Federated learning emerges as a solution, enabling collaborative model training without users directly sharing their raw data. However, integrating federated learning with GNNs presents unique challenges, especially when a client represents a graph node and holds merely a single feature vector. In this paper, we propose a novel framework for node-level federated graph learning. Specifically, we decouple the message-passing and feature vector transformation processes of the first GNN layer, allowing them to be executed separately on the user devices and the cloud server. Moreover, we introduce a graph Laplacian term based on the feature vector's latent representation to regulate the user-side model updates. The experiment results on multiple datasets show that our approach achieves better performance compared with baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_19513 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One Node Per User: Node-Level Federated Learning for Graph Neural Networks Gao, Zhidong Guo, Yuanxiong Gong, Yanmin Machine Learning Artificial Intelligence Graph Neural Networks (GNNs) training often necessitates gathering raw user data on a central server, which raises significant privacy concerns. Federated learning emerges as a solution, enabling collaborative model training without users directly sharing their raw data. However, integrating federated learning with GNNs presents unique challenges, especially when a client represents a graph node and holds merely a single feature vector. In this paper, we propose a novel framework for node-level federated graph learning. Specifically, we decouple the message-passing and feature vector transformation processes of the first GNN layer, allowing them to be executed separately on the user devices and the cloud server. Moreover, we introduce a graph Laplacian term based on the feature vector's latent representation to regulate the user-side model updates. The experiment results on multiple datasets show that our approach achieves better performance compared with baselines. |
| title | One Node Per User: Node-Level Federated Learning for Graph Neural Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2409.19513 |