通过融合结构与节点特征，提升联邦图学习在非独立同分布数据下的性能。
Enhancing Federated Graph Learning via Adaptive Fusion of Structural and Node Characteristics
- 按结构相似性聚类客户端，分组内聚合模型以保留拓扑信息。
- 识别共性节点特征并传播共享模型，提升特征理解能力。
- 在不同分布下精度提升4.94%-7.24%，通信成本降低64.18%-81.25%。
联邦图学习（FGL）能够在分布式客户端上利用本地图数据训练全局图神经网络（GNN）模型。与欧几里得数据（如图像）不同，图数据由节点和边构成，整体节点-边连接决定拓扑结构，而单个节点及其邻居则捕获局部节点特征。然而，现有研究往往偏向某一维度，导致对数据理解不完整，且在不同图场景中易误判关键特征。此外，图数据的非独立同分布（non-IID）特性使两类特征提取更加困难。为此，本文提出新型联邦图学习框架FedGCF，旨在同时提取并融合结构属性与节点特征，以应对多样化图场景。FedGCF首先根据结构相似性对客户端进行聚类，在每个簇内执行模型聚合，形成共享结构模型；随后，选择具有共性节点特征的客户端，聚合其模型生成公共节点模型，并将其传播至所有客户端，实现节点特征共享。通过合理比例组合两个模型，FedGCF能全面理解图数据，在非IID分布下仍表现优异。实验表明，相比基线方法，FedGCF在不同数据分布下准确率提升4.94%-7.24%，达到相同精度时通信成本降低64.18%-81.25%。
原文摘要 · Abstract (English)
Federated Graph Learning (FGL) has demonstrated the advantage of training a global Graph Neural Network (GNN) model across distributed clients using their local graph data. Unlike Euclidean data (\eg, images), graph data is composed of nodes and edges, where the overall node-edge connections determine the topological structure, and individual nodes along with their neighbors capture local node features. However, existing studies tend to prioritize one aspect over the other, leading to an incomplete understanding of the data and the potential misidentification of key characteristics across varying graph scenarios. Additionally, the non-independent and identically distributed (non-IID) nature of graph data makes the extraction of these two data characteristics even more challenging. To address the above issues, we propose a novel FGL framework, named FedGCF, which aims to simultaneously extract and fuse structural properties and node features to effectively handle diverse graph scenarios. FedGCF first clusters clients by structural similarity, performing model aggregation within each cluster to form the shared structural model. Next, FedGCF selects the clients with common node features and aggregates their models to generate a common node model. This model is then propagated to all clients, allowing common node features to be shared. By combining these two models with a proper ratio, FedGCF can achieve a comprehensive understanding of the graph data and deliver better performance, even under non-IID distributions. Experimental results show that FedGCF improves accuracy by 4.94%-7.24% under different data distributions and reduces communication cost by 64.18%-81.25% to reach the same accuracy compared to 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。