Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noise
This paper proposes a hybrid framework called PCC+GCN to improve the robustness of Graph Convolutional Networks (GCNs) to noisy supervision.
The novelty of this paper is the proposal of a hybrid framework that combines PCC and GCN to improve the robustness of GCNs to noisy supervision.
Before reading this…
Applications
- →Graph Classification
- →Graph Neural Networks
To understand this paper, make sure you know these concepts first:
- Graph Convolutional Networksfind papers →
- Particle Competition and Cooperationfind papers →
Abstract
More Like ThisGraph 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.