Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint

Qian, Feifei; Bai, Lu; Cui, Lixin; Li, Ming; Du, Hangyuan; Wang, Yue; Hancock, Edwin

doi:10.24963/ijcai.2025/360

Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint

Feifei Qian, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang, Edwin Hancock

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 3235-3244.

https://doi.org/10.24963/ijcai.2025/360

Keywords

Data Mining: DM: Mining graphs
Machine Learning: ML: Classification
Machine Learning: ML: Deep learning architectures

Abstract

The over-smoothing has emerged as a major challenge in the development of Graph Neural Networks (GNNs). While existing state-of-the-art methods effectively mitigate the diminishing distance between nodes and improve the performance of node classification, they tend to be elusive for graph-level tasks. This paper introduces a novel entropy-based perspective to explore the over-smoothing problem, simultaneously enhancing the distinguishability of non-isomorphic graphs. We provide a theoretical analysis of the relationship between the smoothness and the entropy for graphs, highlighting how the over-smoothing in high-entropic regions negatively impact the graph classification performance. To tackle this issue, we propose a simple yet effective method to Sample and Discretize node features in high-Entropic regions (SDE), aiming to preserve the critical and complicated structural information. Moreover, we introduce a new evaluation metric to assess the over-smoothing for graph-level tasks, focusing on node distributions. Experimental results demonstrate that the proposed SDE method significantly outperforms existing state-of-the-art methods, establishing a new benchmark in the field of GNNs.

Feifei Qian, Lu Bai, Lixin Cui, Ming Li, Hangyuan Du, Yue Wang, and Edwin Hancock. 2025. Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 3235–3244. https://doi.org/10.24963/ijcai.2025/360

@inproceedings{ijcai2025p360,
  title     = {Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint},
  author    = {Qian, Feifei and Bai, Lu and Cui, Lixin and Li, Ming and Du, Hangyuan and Wang, Yue and Hancock, Edwin},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {3235--3244},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/360},
  url       = {https://doi.org/10.24963/ijcai.2025/360},
}

TY  - CPAPER
TI  - Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint
AU  - Qian, Feifei
AU  - Bai, Lu
AU  - Cui, Lixin
AU  - Li, Ming
AU  - Du, Hangyuan
AU  - Wang, Yue
AU  - Hancock, Edwin
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 3235
EP  - 3244
DO  - 10.24963/ijcai.2025/360
UR  - https://doi.org/10.24963/ijcai.2025/360
ER  -