Graph learning method cuts label noise impact and speeds training
Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise
Machine Learning
Summary
Labels in graph data can be wrong and cause errors in learning, which hurts the performance of Graph Convolutional Networks (GCNs). The authors propose a method called PCC+GCN that first cleans up suspicious labels using a process inspired by competing particles moving across the graph. This cleanup helps decide which labels to keep, remove, or change before training the GCN. Their tests show this method works well on many datasets, improving accuracy and running faster than other robust techniques, especially when labels have complex errors.
What this means in practice
- •For data engineers: Improve the quality of graph-labeled datasets by automatically correcting noisy labels before training GCN models.
- •For software teams building recommendation systems: Reduce errors from mislabeled user-item data in graph-based recommendation models to enhance prediction accuracy and training efficiency.
Authors
Fabricio Breve
Abstract
Graph Convolutional Networks (GCNs) are highly sensitive to label noise, since corrupted supervision can propagate through the graph and degrade learned node representations. This work proposes PCC+GCN, a hybrid framework that uses Particle Competition and Cooperation (PCC) as a graph-based label-refinement stage before GCN training. PCC identifies suspicious labeled nodes through particle domination dynamics and determines whether their labels should be preserved, removed, or reassigned before GCN training. The framework also allows the graph used by PCC to be augmented with feature-based $k$-nearest-neighbor edges, while the GCN itself is trained on the original graph structure and node features. The proposed method was evaluated on ten graph datasets from the NoisyGL benchmark under conventional Uniform, Pair, and Random label noise, as well as under instance-dependent label noise. A detailed hyperparameter analysis was also conducted on Cora, CiteSeer, and PubMed. Under conventional noise, PCC+GCN achieved the highest overall average accuracy and the best average rank among the evaluated methods, with an average gain of $1.67$ percentage points over the baseline GCN across the clean setting and all noisy scenarios. Under instance-dependent noise, PCC+GCN remained competitive with the best-performing robust methods while requiring substantially lower execution time, being the fastest robust method on eight of the ten datasets. The results indicate that PCC-based label refinement provides an effective and computationally efficient preprocessing strategy for improving GCN robustness under noisy supervision.