Robust Node Classification on Graph Data with Graph and Label Noise

Current research for node classification focuses on dealing with either graph noise or label noise, but few studies consider both of them. In this paper, we propose a new robust node classification method to simultaneously deal with graph noise and label noise. To do this, we design a graph contrastive loss to conduct local graph learning and employ self-attention to conduct global graph learning. They enable us to improve the expressiveness of node representation by using comprehensive information among nodes. We also utilize pseudo graphs and pseudo labels to deal with graph noise and label noise, respectively. Furthermore, We numerically validate the superiority of our method in terms of robust node classification compared with all comparison methods.

Authors

• Yonghua Zhu Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University Information Systems Technology Design Pillar, Singapore University of Technology and Design
• Lei Feng Singapore University of Technology and Design
• Zhenyun Deng Department of Computer Science, University of Cambridge, UK
• Yang Chen
• Robert Amor School of Computer Science, University of Auckland, NZ
• Michael Witbrock NAOInstitute, University of Auckland, New Zealand School of Computer Science, University of Auckland, New Zealand

Keywords

• ML: Deep Learning Algorithms
• ML: Graph-based Machine Learning
• ML: Representation Learning
• ML: Semi-Supervised Learning