EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SparsePool: A Graph Pooling Framework via Sparse Representation for Graph Classification

Zehan Li iD, Xuemeng Zhai iD, Hangyu Hu iD, Jiandong Liang, Guangmin Hu

Sensors · 23.04.2026 · 26 (9) · 2627

DOI: 10.3390/s26092627 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.04.2026. Verfasst von Zehan Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph neural networks (GNNs) have achieved great success in graph classification, with graph pooling methods being widely adopted for related tasks. Existing approaches typically rely on node ranking or clustering to coarsen graphs, but often fail to effectively leverage global structural information, leading to loss of critical substructures and limited interpretability—key limitations in molecular analysis and social network mining. To address these issues, we propose SparsePool, a graph pooling method that integrates node features and structural patterns through atomic decomposition. By dynamically decomposing graphs into interpretable atomic units via Boolean matrix factorization, SparsePool preserves semantically meaningful substructures while providing transparent evidence of retained patterns. We further introduce an Atomic Pooling Neural Network (APNN) for graph representation learning. Extensive experiments on relevant benchmarks including biochemical and social network datasets demonstrate that SparsePool outperforms state-of-the-art pooling methods, achieving an average classification accuracy improvement of 1.03% over baseline models while reducing structural information loss. We also discuss its compatibility with emerging quantum computing paradigms, such as quantum-accelerated sparse decomposition, as a promising direction for scaling graph processing in industrial contexts.

Schlagwörter

Stichwörter der Autor:innen

graph classificationgraph neural networksquantum computingsparse representation

Autor:innen und Institutionen

  • School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, China.
  • School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.

ORCID-Profile: Zehan Li, Xuemeng Zhai, Hangyu Hu

Zitieren

APA

Li, Z., Zhai, X., Hu, H., Liang, J., & Hu, G. (2026). SparsePool: A Graph Pooling Framework via Sparse Representation for Graph Classification. Sensors, 26(9), 2627. https://doi.org/10.3390/s26092627

Vancouver

Li Z, Zhai X, Hu H, Liang J, Hu G. SparsePool: A Graph Pooling Framework via Sparse Representation for Graph Classification. Sensors. 2026;26(9):2627. doi:10.3390/s26092627

BibTeX
@article{Li2026,
  author = {Li, Zehan and Zhai, Xuemeng and Hu, Hangyu and Liang, Jiandong and Hu, Guangmin},
  title = {SparsePool: A Graph Pooling Framework via Sparse Representation for Graph Classification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {9},
  pages = {2627},
  doi = {10.3390/s26092627}
}
Kostenlos starten →