Conference Paper2021Cited by 1

Structure-aware hierarchical graph pooling using information bottleneck

Kashob Kumar Roy, Amit Roy, AKM Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali

2021 International Joint Conference on Neural Networks (IJCNN)

IEEE, pp. 1–8

DOI: 10.1109/ijcnn52387.2021.9533778Open AccessURL

Abstract

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling and summarizing nodes' features in a graph. However, most existing pooling methods are unable to capture distinguishable structural information effectively. Besides, they are prone to adversarial attacks. In this work, we propose a novel pooling method named as HIBPool where we leverage the Information Bottleneck (IB) principle that optimally balances the expressiveness and robustness of a model to learn representations of input data. Furthermore, we introduce a novel structure-aware Discriminative Pooling Readout (DiP-Readout) function to capture the informative local subgraph structures in the graph. Finally, our experimental results show that our model significantly outperforms other state-of-art methods on several graph classification benchmarks and more resilient to feature-perturbation attack than existing pooling methods11Source code at: https://github.com/forkkr/HIBPool.

Keywords

  • graph pooling
  • information bottleneck
  • adversarial robustness
  • graph neural networks
  • graph classification

CCDS Authors

Kashob Kumar Roy
Kashob Kumar Roy

Kashob Kumar Roy

  • Research Assistant, CCDS

PhD Student

University of Illinois Urbana-Champaign

Published at

PAKDD, IJCNN

Research Interests

Machine Learning

Amit Roy
Amit Roy

Amit Roy

  • Research Assistant, CCDS

PhD Student

Purdue University

Published at

PAKDD, IJCNN

Research Interests

Machine Learning

AKM Mahbubur Rahman, PhD
AKM Mahbubur Rhman, PhD

AKM Mahbubur Rahman, PhD

  • Director, DS & IPT Wings

Associate Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

CHI, ECCV, WACV, PAKDD, LREC, IJCNN, ICPR, ICIP, HCII, BEA, Scientific Reports, Information Sciences

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

Amin Ahsan Ali, PhD
Amin Ahsan Ali, PhD

Amin Ahsan Ali, PhD

  • Director, AI/ML Wing

Professor

Department of Computer Science and Engineering

Independent University, Bangladesh

Published at

ACL, CHI, UbiComp, ECCV, IJCAI, ECAI, WACV, IPSN, PAKDD, LREC, IJCNN, ICPR, ICIP, BEA, BLP, ICMLA, Scientific Reports, Scientific Data, Pattern Recognition, Information Sciences, Ad Hoc Networks, Drug and Alcohol Dependence, PLOS ONE

Research Interests

Artificial Intelligence, Machine Learning

References

  1. 1.Vincent D. Blondel, Jean‐Loup Guillaume, Renaud Lambiotte, Etienne Lefebvre. (2008). Fast unfolding of communities in large networks. Journal of Statistical Mechanics Theory and Experiment, 2008(10), P10008[10.1088/1742-5468/2008/10/p10008]
  2. 2.Chen, Tianyu, Wang, Zeyu, Li, Lin, Li, Ding, Li, Zongyang, Chang, Xiaoning, Bian, Pan, Liang, Guangtai, Wang, Qianxiang, Xie, Tao. (2025). Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories. Dagstuhl Research Online Publication Server[10.4230/lipics.ecoop.2025.6]
  3. 3.Michelle Girvan, M. E. J. Newman. (2002). Community structure in social and biological networks. Proceedings of the National Academy of Sciences, 99(12), 7821–7826[10.1073/pnas.122653799]
  4. 4.Michelle G. Newman, Michelle Girvan. (2004). Finding and evaluating community structure in networks. Physical Review E, 69(2), 026113[10.1103/physreve.69.026113]
  5. 5.M. E. J. Newman. (2006). Modularity and community structure in networks. Proceedings of the National Academy of Sciences, 103(23), 8577–8582[10.1073/pnas.0601602103]
  6. 6.Santo Fortunato. (2009). Community detection in graphs. Physics Reports, 486(3-5), 75–174[10.1016/j.physrep.2009.11.002]
  7. 7.M. E. J. Newman. (2004). Fast algorithm for detecting community structure in networks. Physical Review E, 69(6), 066133[10.1103/physreve.69.066133]
  8. 8.Tian Xie, Jeffrey C. Grossman. (2018). Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. Physical Review Letters, 120(14), 145301[10.1103/physrevlett.120.145301]
  9. 9.Luciano da Fontoura Costa, Francisco A. Rodrigues, Gonzalo Travieso, Paulino Ribeiro Villas-Boas. (2007). Characterization of complex networks: A survey of measurements. Advances In Physics, 56(1), 167–242[10.1080/00018730601170527]
  10. 10.Muhan Zhang, Zhicheng Cui, Marion Neumann, Yixin Chen. (2018). An End-to-End Deep Learning Architecture for Graph Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1)[10.1609/aaai.v32i1.11782]
  11. 11.Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, Jure Leskovec. (2018). Hierarchical graph representation learning with differentiable pooling. Neural Information Processing Systems, 31, 4805–4815
  12. 12.Ekagra Ranjan, Soumya Sanyal, Partha Talukdar. (2020). ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations. [10.1609/aaai.v34i04.5997]
  13. 13.Sara Rahiminejad, Mano R. Maurya, Shankar Subramaniam. (2019). Topological and functional comparison of community detection algorithms in biological networks. BMC Bioinformatics, 20(1), 212[10.1186/s12859-019-2746-0]
  14. 14.Hongyang Gao, Shuiwang Ji. (2019). Graph U-Nets. International Conference on Machine Learning, 2083–2092
  15. 15.Pratha Sah, Lisa Singh, Aaron Clauset, Shweta Bansal. (2014). Exploring community structure in biological networks with random graphs. BMC Bioinformatics, 15(1), 220[10.1186/1471-2105-15-220]
  16. 16.Gabriele Corso, Luca Cavalleri, Dominique Beaini, Píetro Lió, Petar Veličković. (2020). Principal Neighbourhood Aggregation for Graph Nets. Neural Information Processing Systems, 33, 13260–13271
  17. 17.Hui Yao, David M. Kristensen, Ivana Mihalek, Mathew E. Sowa, Chad A. Shaw, Marek Kimmel, Lydia E. Kavraki, Olivier Lichtarge. (2003). An Accurate, Sensitive, and Scalable Method to Identify Functional Sites in Protein Structures. Journal of Molecular Biology, 326(1), 255–261[10.1016/s0022-2836(02)01336-0]
  18. 18.Pascal Pons, Matthieu Latapy. (2010). Post-processing hierarchical community structures: Quality improvements and multi-scale view. Theoretical Computer Science, 412(8-10), 892–900[10.1016/j.tcs.2010.11.041]
  19. 19.Yu Zhou, Haixia Zheng, Xin Huang, Shufeng Hao, Dengao Li, Jumin Zhao. (2022). Graph Neural Networks: Taxonomy, Advances, and Trends. ACM Transactions on Intelligent Systems and Technology, 13(1), 1–54[10.1145/3495161]
  20. 20.Diego Mesquita, Amauri H. Souza, Samuel Kaski. (2020). Rethinking pooling in graph neural networks. Aaltodoc (Aalto University), 33, 2220–2231[link]
  21. 21.Tailin Wu, Hongyu Ren, Pan Li, Jure Leskovec. (2020). Graph Information Bottleneck. Neural Information Processing Systems, 33, 20437–20448
  22. 22.Omar Gaci. (2011). Community structure description in amino acid interaction networks. Interdisciplinary Sciences Computational Life Sciences, 3(1), 50–56[10.1007/s12539-011-0061-1]
  23. 23.Davide Bacciu, Alessio Conte, Roberto Grossi, Francesco Landolfi, Andrea Marino. (2021). K-plex cover pooling for graph neural networks. Data Mining and Knowledge Discovery, 35(5), 2200–2220[10.1007/s10618-021-00779-z]
  24. 24.William L. Hamilton, Rex Ying, Jure Leskovec. (2017). Inductive Representation Learning on Large Graphs. arXiv (Cornell University), 30, 1024–1034[10.48550/arxiv.1706.02216]
  25. 25.Zhukov, Georgy Alexandrovich. (2025). Formal Semantics for Kolmogorov-Arnold Network Representations of Operational Games. Zenodo (CERN European Organization for Nuclear Research)[10.5281/zenodo.15206559]
  26. 26.Tishby, Naftali, Fernando C. N. Pereira, William Bialek. (2000). The information bottleneck method. ArXiv.org[10.48550/arxiv.physics/0004057]
  27. 27.Cătălina Cangea, Petar Veličković, Nikola Jovanović, Thomas Kipf, Píetro Lió. (2018). Towards Sparse Hierarchical Graph Classifiers. arXiv (Cornell University)[10.48550/arxiv.1811.01287]
  28. 28.Soumya Sanyal, Janakiraman Balachandran, Naganand Yadati, Abhishek Kumar, Padmini Rajagopalan, Suchismita Sanyal, Partha Talukdar. (2018). MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction. arXiv (Cornell University)[10.48550/arxiv.1811.05660]
  29. 29.Enxhell Luzhnica, Ben Day, Píetro Lió. (2019). Clique pooling for graph classification. arXiv (Cornell University)[10.48550/arxiv.1904.00374]

Cited By

  1. 1.Chuang Liu, Yibing Zhan, Jia Wu, Chang Li, Bo Du, Wenbin Hu, Tongliang Liu, Dacheng Tao. (2023). Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities. , 6712–6722[10.24963/ijcai.2023/752]
← All publications