解决无图客户端的联邦图学习问题，让只拥有节点特征的客户端也能参与训练。
Federated Graph Learning with Graphless Clients
- 为无图客户端设计局部图结构学习器，通过知识迁移获取图结构信息。
- 在多个数据集上性能超越5个基线方法，尤其在低图数据比例下优势显著。
- 适合实际中存在大量仅有特征而无图结构的联邦学习场景。
联邦图学习（FGL）旨在为多个客户端联合训练机器学习模型，如图神经网络（GNN），每个客户端拥有自己的图数据。现有方法通常假设每个客户端同时具备节点特征和图结构。但在真实场景中，部分客户端可能仅拥有节点特征而无图结构（即无图客户端）。这引出了一个新问题：如何在包含无图客户端的情况下，联合训练分布式图数据上的模型？本文提出新框架FedGLS以解决该问题。在FedGLS中，每个无图客户端部署一个局部图学习器，利用其他客户端传递的结构知识来学习本地图结构。为实现结构知识迁移，每个客户端设计了GNN模型和特征编码器。本地训练时，特征编码器通过知识蒸馏保留来自GNN的结构知识，并在全局更新中实现客户端间知识传递。大量实验表明，所提方法在多个基准上优于5个基线，尤其在图数据稀疏场景表现更优。
原文摘要 · Abstract (English)
Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments demonstrate the superiority of the proposed FedGLS over five 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。