English

Structure-Aware Label Smoothing for Graph Neural Networks

Machine Learning 2021-12-02 v1 Artificial Intelligence Social and Information Networks

Abstract

Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect the semantic characteristics of a node in different classes, as some nodes may be semantically close to their neighbors in other classes. It would cause over-confidence since the models are encouraged to assign full probabilities when classifying every node. While training models with label smoothing can ease this problem to some degree, it still fails to capture the nodes' semantic characteristics implied by the graph structures. In this work, we propose a novel SALS (\textit{Structure-Aware Label Smoothing}) method as an enhancement component to popular node classification models. SALS leverages the graph structures to capture the semantic correlations between the connected nodes and generate the structure-aware label distribution to replace the original one-hot label vectors, thus improving the node classification performance without inference costs. Extensive experiments on seven node classification benchmark datasets reveal the effectiveness of our SALS on improving both transductive and inductive node classification. Empirical results show that SALS is superior to the label smoothing method and enhances the node classification models to outperform the baseline methods.

Keywords

Cite

@article{arxiv.2112.00499,
  title  = {Structure-Aware Label Smoothing for Graph Neural Networks},
  author = {Yiwei Wang and Yujun Cai and Yuxuan Liang and Wei Wang and Henghui Ding and Muhao Chen and Jing Tang and Bryan Hooi},
  journal= {arXiv preprint arXiv:2112.00499},
  year   = {2021}
}
R2 v1 2026-06-24T07:59:37.711Z