mlsanityData to 7 Oct 2026

ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity

arXiv 2510.03987 ↗First posted 5 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Hierarchical Pooling Models have demonstrated strong performance in classifying graph-structured data. While numerous innovative methods have been proposed to design cluster assignments and coarsening strategies, the relationships between clusters are often overlooked. In this paper, we introduce Inter-cluster Connectivity Enhancement Pooling (ICEPool), a novel hierarchical pooling framework designed to enhance model's understanding of inter-cluster connectivity and ability of preserving the structural integrity in the original graph. ICEPool is compatible with a wide range of pooling-based GNN models. The deployment of ICEPool as an enhancement to existing models effectively combines the strengths of the original model with ICEPool's capability to emphasize the integration of inter-cluster connectivity, resulting in a more comprehensive and robust graph-level representation. Moreover, we make theoretical analysis to ICEPool's ability of graph reconstruction to demonstrate its effectiveness in learning inter-cluster relationship that is overlooked by conventional models. Finally, the experimental results show the compatibility of ICEPool with wide varieties of models and its potential to boost the performance of existing graph neural network architectures.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 5 Oct 2025.

Builds on

29 of 38 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  8. 2018Link Prediction Based on Graph Neural Networkscited by 829
  9. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  10. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  11. 2019Heterogeneous Graph Attention Networkcited by 732
  12. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
17 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 711
  2. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  3. 2019Graph Transformer Networkscited by 520
  4. 2019Graph U-Netscited by 489
  5. 2019Self-Attention Graph Poolingcited by 421
  6. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  7. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
  8. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  9. 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
  10. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 132
  11. 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
  12. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  13. 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
  14. 2019Semi-Supervised Graph Classification: A Hierarchical Graph Perspectivecited by 55
  15. 2020Spectral Algorithms for Community Detection in Directed Networkscited by 17
  16. 2024Cluster-wise Graph Transformer with Dual-granularity Kernelized Attentioncited by 8
  17. 2020Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networkscited by 7

Built on by

Not cited yet.