A unified benchmark of 18 federated learning methods under synthetic, human-annotation, and systematic label noise finds no consistently winning method and shows that an SVD-based decorrelation regularizer improves most baselines.
FedRGL: Robust Federated Graph Learning for Label Noise
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FNBench: Benchmarking Robust Federated Learning against Noisy Labels
A unified benchmark of 18 federated learning methods under synthetic, human-annotation, and systematic label noise finds no consistently winning method and shows that an SVD-based decorrelation regularizer improves most baselines.