---
title: "Exploring the Over-smoothing Problem of Graph Neural Networks for Graph Classification: An Entropy-based Viewpoint"
authors:
  - "Feifei Qian"
  - "Lu Bai"
  - "Lixin Cui"
  - "Ming Li"
  - "Hangyuan Du"
  - "Yue Wang"
  - "Edwin Hancock"
doi: "10.24963/ijcai.2025/360"
url: "https://ijcai.org/proceedings/2025/360"
pdf: "https://ijcai.org/proceedings/2025/0360.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3235-3244"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining graphs"
  - "Machine Learning: ML: Classification"
  - "Machine Learning: ML: Deep learning architectures"
---

# 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

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3235-3244. DOI: [10.24963/ijcai.2025/360](https://doi.org/10.24963/ijcai.2025/360)

## 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.