Noisy Node Classification by Bi-level Optimization Based Multi-Teacher Distillation

Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model. Finally, we design a label improvement module to improve the label quality. Extensive experimental results on real datasets show that our method achieves the best results compared to state-of-the-art methods.

Authors

• Yujing Liu Guangxi Normal University
• Zongqian Wu University of Electronic Science and Technology of China
• Zhengyu Lu Guangxi Normal University Anyang Institute of Technology
• Ci Nie Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University
• Guoqiu Wen Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University
• Yonghua Zhu Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University Information Systems Technology Design Pillar, Singapore University of Technology and Design
• Xiaofeng Zhu Guangxi Key Lab of Multisource Information Mining Security, Guangxi Normal University School of Computer Science and Engineering, University of Electronic Science and Technology of China

Keywords

No keywords are indexed for this paper.