DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise

arXiv:2404.09207v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have achieved notable success in various applications over graph data. However, recent research has revealed that real-world graphs often contain noise, and GNNs are susceptible to noise in the graph. To address this issue, several Graph Structure Learning (GSL) models have been introduced. While GSL models are tailored to enhance robustness against edge noise through edge reconstruction, a significant limitation surfaces: their high reliance on node features. This inherent dependence amplifies …

abstract applications arxiv cs.lg data edge experts feature gnns graph graph data graph neural network graph neural networks graphs however issue network networks neural network neural networks node noise research success the graph type world