Towards Robust Graph Neural Networks against Label Noise

Jun Xia, Haitao Lin, Yongjie Xu, Lirong Wu, Zhangyang Gao, Siyuan Li, Stan Z. Li

Keywords: Graph Neural Networks, Graph Node Classification, Label Noise

Abstract: Massive labeled data have been used in training deep neural networks, thus label noise has become an important issue therein. Although learning with noisy labels has made great progress on image datasets in recent years, it has not yet been studied in connection with utilizing GNNs to classify graph nodes. In this paper, we proposed a method, named LPM, to address the problem using Label Propagation (LP) and Meta learning. Different from previous methods designed for image datasets, our method is based on a special attribute (label smoothness) of graph-structured data, i.e., neighboring nodes in a graph tend to have the same label. A pseudo label is computed from the neighboring labels for each node in the training set using LP; meta learning is utilized to learn a proper aggregation of the original and pseudo label as the final label. Experimental results demonstrate that LPM outperforms state-of-the-art methods in graph node classification task with both synthetic and real-world label noise. Source code to reproduce all results will be released.

One-sentence Summary: To the best of our knowledge, we are the first to focus on the label noise existing in utilizing GNNs to classify graph nodes.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=UW4yOOs9Yw