用自适应采样提升联邦图神经网络的个性化训练效果
FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
- 基于生成流网络评估节点重要性，动态调整消息传递
- 在多个数据集上显著优于基线方法，提升模型性能
- 适合处理客户端子图异构性强的隐私保护场景
图数据在建模关系与生物数据中至关重要。随着现实场景中数据集规模增大，敏感信息泄露风险上升，隐私保护训练方法如联邦学习（FL）成为确保数据安全和符合隐私法规的关键。近期提出的个性化子图联邦学习方法已成为在联邦环境中训练个性化图神经网络（GNN）的主流方案，但因隐私限制导致客户端子图间存在缺失链接，仍面临挑战。尤其当客户端子图在节点度分布等方面存在异质性时，联邦训练难度加剧。为此，我们提出FedGrAINS，一种基于生成流网络（GFlowNets）的数据自适应、采样正则化方法。该方法通过评估节点对客户端任务的重要性，动态调整客户端GNN中的消息传递步骤，实现与轨迹平衡目标一致的任务优化采样。实验表明，将FedGrAINS作为正则化器可持续提升联邦学习性能，优于未采用此类正则化的基线方法。
原文摘要 · Abstract (English)
Graphs are crucial for modeling relational and biological data. As datasets grow larger in real-world scenarios, the risk of exposing sensitive information increases, making privacy-preserving training methods like federated learning (FL) essential to ensure data security and compliance with privacy regulations. Recently proposed personalized subgraph FL methods have become the de-facto standard for training personalized Graph Neural Networks (GNNs) in a federated manner while dealing with the missing links across clients' subgraphs due to privacy restrictions. However, personalized subgraph FL faces significant challenges due to the heterogeneity in client subgraphs, such as degree distributions among the nodes, which complicate federated training of graph models. To address these challenges, we propose \textit{FedGrAINS}, a novel data-adaptive and sampling-based regularization method for subgraph FL. FedGrAINS leverages generative flow networks (GFlowNets) to evaluate node importance concerning clients' tasks, dynamically adjusting the message-passing step in clients' GNNs. This adaptation reflects task-optimized sampling aligned with a trajectory balance objective. Experimental results demonstrate that the inclusion of \textit{FedGrAINS} as a regularizer consistently improves the FL performance compared to baselines that do not leverage such regularization.
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。