DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise
Preprint
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 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.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Hybrid graph convolution neural network and branch-and-bound optimization for traffic flow forecastingFuture Generation Computer Systems, 2022
- Simplifying approach to node classification in Graph Neural NetworksJournal of Computational Science, 2022
- Graph Self-Supervised Learning: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2022
- Predicting Emergency Medical Service Demand With Bipartite Graph Convolutional NetworksIEEE Access, 2021
- Graph Structure Learning for Robust Graph Neural Networks2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Fast Approximations of Betweenness Centrality with Graph Neural Networks2019
- Robust Graph Convolutional Networks Against Adversarial Attacks2019
- Graph Neural Networks for Social Recommendation2019
- Learning Community Structure with Variational Autoencoder2018