English

Addressing Over-Smoothing in Graph Neural Networks via Deep Supervision

Machine Learning 2022-02-28 v1

Abstract

Learning useful node and graph representations with graph neural networks (GNNs) is a challenging task. It is known that deep GNNs suffer from over-smoothing where, as the number of layers increases, node representations become nearly indistinguishable and model performance on the downstream task degrades significantly. To address this problem, we propose deeply-supervised GNNs (DSGNNs), i.e., GNNs enhanced with deep supervision where representations learned at all layers are used for training. We show empirically that DSGNNs are resilient to over-smoothing and can outperform competitive benchmarks on node and graph property prediction problems.

Keywords

Cite

@article{arxiv.2202.12508,
  title  = {Addressing Over-Smoothing in Graph Neural Networks via Deep Supervision},
  author = {Pantelis Elinas and Edwin V. Bonilla},
  journal= {arXiv preprint arXiv:2202.12508},
  year   = {2022}
}
R2 v1 2026-06-24T09:53:27.301Z