FedRGL: Robust Federated Graph Learning for Label Noise
This addresses label noise in federated graph learning for distributed graph data applications, representing an incremental improvement over existing methods.
The paper tackles label noise in federated graph learning, which degrades model generalization, by proposing FedRGL, a method that uses dual-perspective consistency filtering and graph contrastive learning to achieve superior performance, outperforming 12 baselines across various noise conditions.
Federated Graph Learning (FGL) is a distributed machine learning paradigm based on graph neural networks, enabling secure and collaborative modeling of local graph data among clients. However, label noise can degrade the global model's generalization performance. Existing federated label noise learning methods, primarily focused on computer vision, often yield suboptimal results when applied to FGL. To address this, we propose a robust federated graph learning method with label noise, termed FedRGL. FedRGL introduces dual-perspective consistency noise node filtering, leveraging both the global model and subgraph structure under class-aware dynamic thresholds. To enhance client-side training, we incorporate graph contrastive learning, which improves encoder robustness and assigns high-confidence pseudo-labels to noisy nodes. Additionally, we measure model quality via predictive entropy of unlabeled nodes, enabling adaptive robust aggregation of the global model. Comparative experiments on multiple real-world graph datasets show that FedRGL outperforms 12 baseline methods across various noise rates, types, and numbers of clients.