A noise-resistant graph neural network by semi-supervised contrastive learning

Zhengyu Lu, Junbo Ma, Zongqian Wu, Bo Zhou, Xiaofeng Zhu

Abstract: Highlights•Propose a new noise-resistant graph neural network to conduct representation learning on the graph data with noisy labels.•Propose a semi-supervised contrastive learning constraint to push noisy nodes away from unlabeled nodes in embedding space.•Intuitively analyze the feasibility of the proposed constraint.