An End-to-End Simple Clustering Hierarchical Pooling Operation for Graph Learning Based on Top-K Node Selection

Zhao, Zhehan; Bai, Lu; Li, Ming; Cui, Lixin; Du, Hangyuan; Wang, Yue; Hancock, Edwin

doi:10.24963/ijcai.2025/408

An End-to-End Simple Clustering Hierarchical Pooling Operation for Graph Learning Based on Top-K Node Selection

Zhehan Zhao, Lu Bai, Ming Li, Lixin Cui, Hangyuan Du, Yue Wang, Edwin Hancock

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 3670-3679.

https://doi.org/10.24963/ijcai.2025/408

Keywords

Data Mining: DM: Mining graphs

Abstract

Graph Neural Networks (GNNs) are powerful tools for graph learning, but one of the important challenges is how to effectively extract representations for graph-level tasks. In this paper, we propose an end-to-end Simple Clustering Hierarchical Pooling (SCHPool) operation, which is based on Top-K node selection for learning expressive graph representations. Specifically, SCHPool considers each node and its local neighborhood as a cluster, and introduces a novel multi-view scoring function to evaluate node importance. Based on these scores, clusters centered around the Top-K nodes are retained. This design eliminates the need for complex clustering operations, significantly reducing computational overhead. Furthermore, during the coarsening process, SCHPool employs a lightweight yet comprehensive attention mechanism to adaptively aggregate both the node features within clusters and the edge connectivity strengths between clusters. This facilitates the construction of more informative coarsened graphs, enhancing model performance. Experimental results demonstrate the effectiveness of the proposed model.

Zhehan Zhao, Lu Bai, Ming Li, Lixin Cui, Hangyuan Du, Yue Wang, and Edwin Hancock. 2025. An End-to-End Simple Clustering Hierarchical Pooling Operation for Graph Learning Based on Top-K Node Selection. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 3670–3679. https://doi.org/10.24963/ijcai.2025/408

@inproceedings{ijcai2025p408,
  title     = {An End-to-End Simple Clustering Hierarchical Pooling Operation for Graph Learning Based on Top-K Node Selection},
  author    = {Zhao, Zhehan and Bai, Lu and Li, Ming and Cui, Lixin 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     = {3670--3679},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/408},
  url       = {https://doi.org/10.24963/ijcai.2025/408},
}

TY  - CPAPER
TI  - An End-to-End Simple Clustering Hierarchical Pooling Operation for Graph Learning Based on Top-K Node Selection
AU  - Zhao, Zhehan
AU  - Bai, Lu
AU  - Li, Ming
AU  - Cui, Lixin
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  - 3670
EP  - 3679
DO  - 10.24963/ijcai.2025/408
UR  - https://doi.org/10.24963/ijcai.2025/408
ER  -