DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
This addresses the vulnerability of Graph Neural Networks to noise in real-world graphs, offering a solution for applications relying on graph data, though it appears incremental by building on existing GSL methods.
The paper tackles the problem of noise in both edges and node features in graph data, which existing Graph Structure Learning models fail to handle adequately, and introduces DEGNN, a model that uses dual experts to modify edges and node features, achieving robustness as demonstrated in experiments on real-world and synthetic noisy graphs.
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 their susceptibility to noise within node features. Recognizing this vulnerability, we present DEGNN, a novel GNN model designed to adeptly mitigate noise in both edges and node features. The core idea of DEGNN is to design two separate experts: an edge expert and a node feature expert. These experts utilize self-supervised learning techniques to produce modified edges and node features. Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs. Notably, the modification process can be trained end-to-end, empowering DEGNN to adjust dynamically and achieves optimal edge and node representations for specific tasks. Comprehensive experiments demonstrate DEGNN's efficacy in managing noise, both in original real-world graphs and in graphs with synthetic noise.