解决图神经网络联邦学习中用户数据隐私问题
One Node Per User: Node-Level Federated Learning for Graph Neural Networks
- 将GNN第一层拆分为设备端与云端分步计算
- 引入基于隐向量的图拉普拉斯项约束更新
- 在多个数据集上优于现有基线方法
图神经网络（GNN）训练通常需要将原始用户数据集中到服务器，引发严重隐私担忧。联邦学习提供了一种解决方案，可在不直接共享原始数据的情况下协同训练模型。然而，将联邦学习与GNN结合面临独特挑战，尤其当客户端代表一个图节点且仅持有单一特征向量时。本文提出一种新型节点级联邦图学习框架。具体地，我们解耦了GNN第一层的消息传递与特征向量变换过程，使其可分别在用户设备和云端执行。此外，我们引入基于特征向量潜在表示的图拉普拉斯项，以调控用户端模型更新。在多个数据集上的实验结果表明，该方法性能优于基线方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。