Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation

Abstract

Node classification using Graph Neural Networks (GNNs) has been widely applied in various real-world scenarios. However, in recent years, compelling evidence emerges that the performance of GNN-based node classification may deteriorate substantially by topological perturbation, such as random connections or adversarial attacks. Various solutions, such as topological denoising methods and mechanism design methods, have been proposed to develop robust GNN-based node classifiers but none of these works can fully address the problems related to topological perturbations. Recently, the Bayesian label transition model is proposed to tackle this issue but its slow convergence may lead to inferior performance. In this work, we propose a new label inference model, namely LInDT, which integrates both Bayesian label transition and topology-based label propagation for improving the robustness of GNNs against topological perturbations. LInDT is superior to existing label transition methods as it improves the label prediction of uncertain nodes by utilizing neighborhood-based label propagation leading to better convergence of label inference. Besides, LIndT adopts asymmetric Dirichlet distribution as a prior, which also helps it to improve label inference. Extensive experiments on five graph datasets demonstrate the superiority of LInDT for GNN-based node classification under three scenarios of topological perturbations.

The paper is accepted for CIKM 2022

References in corpus (10)

• Explaining and Harnessing Adversarial Examples
• Towards Deeper Graph Neural Networks
• DivideMix: Learning with Noisy Labels as Semi-supervised Learning
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Learning Graph Neural Networks with Noisy Labels
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• Understanding Structural Vulnerability in Graph Convolutional Networks
• Node Copying: A Random Graph Model for Effective Graph Sampling