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

08/21/2022
by   Jun Zhuang, et al.
0

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.

READ FULL TEXT
research
04/21/2022

Detecting Topology Attacks against Graph Neural Networks

Graph neural networks (GNNs) have been widely used in many real applicat...
research
10/27/2022

Bayesian Inference of Transition Matrices from Incomplete Graph Data with a Topological Prior

Many network analysis and graph learning techniques are based on models ...
research
10/27/2020

Anti-perturbation of Online Social Networks by Graph Label Transition

Numerous popular online social networks (OSN) would classify users into ...
research
10/16/2016

Dynamic Stacked Generalization for Node Classification on Networks

We propose a novel stacked generalization (stacking) method as a dynamic...
research
04/29/2023

Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

In node classification using graph neural networks (GNNs), a typical mod...
research
03/06/2023

DR-Label: Improving GNN Models for Catalysis Systems by Label Deconstruction and Reconstruction

Attaining the equilibrium state of a catalyst-adsorbate system is key to...
research
01/21/2017

Label Propagation on K-partite Graphs with Heterophily

In this paper, for the first time, we study label propagation in heterog...

Please sign up or login with your details

Forgot password? Click here to reset