GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy

Wen Li (Xiamen University) · Jiawei Sun (Rensselaer Polytechnic Institute) · Wei Zhao (Shenzhen Univ of Advanced Technology) · Kailai Li (Shanghai Jiao Tong University) · Jiong Lou (Shanghai Jiao Tong University) · Honghong Zeng (Shanghai Jiaotong University) · Chentao Wu (Shanghai Jiao Tong University,) · Yuan Luo (Shanghai Jiao Tong University) · shouguo du · Jie LI (Shanghai Jiao Tong University)

differentiated supervisiondual-view predictionego-viewgraph neural networkslabel noise detectionmislabeled nodesnode-neighbor interdependenciesnoise-aware frameworknoise-robust learningprediction discrepanciesprediction divergencesemantic coherence state-of-the-art baselinesstructure-viewview-specific training strategy

Graph Neural Networks (GNNs) achieve strong performance in node classification tasks but exhibit substantial performance degradation under label noise. Despite recent advances in noise-robust learning, a principled approach that exploits the node-neighbor interdependencies inherent in graph data for label noise detection remains underexplored. To address this gap, we propose GD$^2$, a noise-aware \underline{G}raph learning framework that detects label noise by leveraging \underline{D}ual-view prediction \underline{D}iscrepancies. The framework contrasts the \textit{ego-view}, constructed from node-specific features, with the \textit{structure-view}, derived through the aggregation of neighboring representations. The resulting discrepancy captures disruptions in semantic coherence between individual node representations and the structural context, enabling effective identification of mislabeled nodes. Building upon this insight, we further introduce a view-specific training strategy that enhances noise detection by amplifying prediction divergence through differentiated view-specific supervision. Extensive experiments on multiple datasets and noise settings demonstrate that \name~achieves superior performance over state-of-the-art baselines.