TY - GEN
T1 - Robust Node Classification on Graphs
T2 - 31st ACM International Conference on Information and Knowledge Management, CIKM 2022
AU - Zhuang, Jun
AU - Al Hasan, Mohammad
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/17
Y1 - 2022/10/17
N2 - 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.
AB - 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.
KW - adversarial defense
KW - bayesian inference
KW - graph neural networks
UR - http://www.scopus.com/inward/record.url?scp=85140851546&partnerID=8YFLogxK
U2 - 10.1145/3511808.3557437
DO - 10.1145/3511808.3557437
M3 - Conference contribution
AN - SCOPUS:85140851546
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 2795
EP - 2805
BT - CIKM 2022 - Proceedings of the 31st ACM International Conference on Information and Knowledge Management
Y2 - 17 October 2022 through 21 October 2022
ER -