Graph Pooling

Follow this topic Ask about this topic

Graph pooling studies how to coarsen a graph into a smaller representation for tasks such as graph classification, clustering, and question answering. Methods learn node-to-cluster assignments or use spectral and community structure, curvature, higher-order topology, and adaptive granularity to build pooled graphs or hierarchical representations. These approaches are used with graph neural networks across settings including molecules, social networks, brain connectivity, and language. A central challenge is balancing computational savings with preservation of task-relevant information: pooling quality can depend on how well node features align with topology and on which graph properties the downstream task requires.

Latest papers

14 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks
Oct 24, 2026Bohan Yoon, Hyejin JangGraph Pooling Hierarchical GNNs
Institute Multiscale Matter and Systems, Ewha Womans University, Seoul, Republic of Korea · Division of AI Data Convergence, Hankuk University of Foreign Studies, Yongin-si, Gyeonggi-do, Republic of Korea
From Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Vehicle Routing Problem
Oct 20, 2026Sofiene Lassoued, Devara Tertia, Stefan Lier +1Pointer Networks Combinatorial Optimization
South Westphalia University of Applied Sciences, Automation Technology and Learning Systems Luebecker Ring 2, Soest, 59494, North Rhine-Westphalia, Germany · South Westphalia University of Applied Sciences, Logistik und Supply Chain Management Lindenstr.53, Meschede, 59872, North Rhine-Westphalia, Germany
Geometric Flow enhanced Graph Coarsening
Sep 14, 2026Chaoqun Fei, Guoxuan Li, Tinglve Zhou +2Graph Neural Networks Graph Coarsening
School of Artificial Intelligence, South China Normal University, Foshan 528225, China · State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China
Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball
Sep 4, 2026Sen Zhao, Gaojie Xu, Shuyin Xia +4Graph Pooling Hierarchical Representation Learning
Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling
Aug 4, 2026Nelson Aloysio Reis de Almeida Passos, Emanuele Carlini, Salvatore TraniGraph Neural Networks Graph Pooling
University of Pisa, Dept. of Computer Science, 56127 Pisa PI, Italy · National Research Council, 56124 Pisa PI, Italy
MPP-GNN: Subject-Adaptive Community Detection for fMRI-Based Alzheimer's Disease Classification
Jul 29, 2026Yang Zhang, Xiao Zhou, Jonathan Warrell +3Graph Neural Networks Graph Pooling
Program in Computational Biology and Bioinformatics, Yale University, New Haven, CT 06520 USA · Department of Psychiatry, Robert Wood Johnson Medical School, and the Brain Health Institute, Rutgers University, Piscataway, NJ 08854 USA · School of Design, Pratt Institute, New York, NY 11205 USA
Hierarchical Pooling for Sheaf Neural Networks
Jun 18, 2026Dionisia Naddeo, Carlo Abate, Pietro Liò +2Graph Neural Networks Graph Coarsening
UiT The Arctic University of Norway · UiT The Arctic University of Norway NORCE Norwegian Research Centre AS
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
Jun 10, 2026Anton Firc, Vojtěch Staněk, Zbyněk Lička +2Efficient Neural Network Inference Graph Neural Networks
The Role of Node Features in Graph Pooling
May 7, 2026Jan von Pichowski, Alžbeta Hrabošová, Ingo Scholtes +1Graph Neural Networks Graph Pooling
Center for AI and Data Science University of Würzburg, Germany · Department of Computing Science Umeå University, Sweden
PUFFIN: Protein Unit Discovery with Functional Supervision
Apr 16, 2026Gökçe Uludoğan, Buse Giledereli, Elif Ozkirimli +1Graph Pooling
Department of Computer Engineering Boğaziçi University Istanbul, Türkiye · Roche Informatics F. Hoffmann-La Roche AG Basel, Switzerland
Is One Token All It Takes? Graph Pooling Tokens for LLM-based GraphQA
Apr 1, 2026Ankit Grover, Lodovico Giaretta, Rémi Bourgerie +1LLM Reasoning with Graphs Graph Pooling
KTH Royal Institute of Technology, Stockholm, Sweden · RISE Research Institutes of Sweden, Stockholm, Sweden
Towards Improved Sentence Representations using Token Graphs
Mar 3, 2026Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Zorah Lähner +1Sentence Embeddings Graph Pooling
University of Bonn · Lamarr Institute for Machine Learning and Artificial Intelligence · University of Cambridge +1
Point-Voxel Absorbing Graph Representation Learning for Event Stream based Recognition
Jun 8, 2023Yuxiang Zhang, Chengguo Yuan, Xiao Wang +2Event-Based Vision Graph Neural Networks
aSchool of Computer Science and Technology, Anhui University, Hefei 230601, China.
NervePool: A Simplicial Pooling Layer
May 10, 2023Sarah McGuire Scullen, Ernst Röell, Elizabeth Munch +2Graph Coarsening Graph Pooling
Pacific Northwest National Lab, USA · Helmholtz Munich and Technical University of Munich, Germany · Michigan State University, USA +1

Oct 24, 2026J/K move · Enter open · S save

Graph-dependent pooling: adaptive granularity in hierarchical graph neural networks

Bohan Yoon, Hyejin Jang

Institute Multiscale Matter and Systems, Ewha Womans University, Seoul, Republic of Korea · Division of AI Data Convergence, Hankuk University of Foreign Studies, Yongin-si, Gyeonggi-do, Republic of Korea

Graph Pooling Hierarchical GNNs

Open paper AskPDF arXiv

Graph Neural Networks are widely used to learn structural representations of relational data. Hierarchical graph pooling learns multi-level representations by progressively coarsening graphs; however, prior methods rely on predefined cluster numbers or fixed pooling ratios, limiting adaptability to individual graphs. We propose Graph-Dependent Pooling (GDPool), which dynamically determines pooling granularity for each graph. We analyze optimization conflicts among layer-wise objectives through gradient alignment, showing that independently supervised pooling levels can send conflicting gradients to shared parameters. GDPool uses self-attention to select graph-specific anchors representing structurally important nodes and constructs coarse graphs through soft node assignment. Experiments on metal-organic framework and molecular graph benchmarks show that GDPool consistently achieves the best predictive performance across all benchmarks. Evaluations using modularity and the effective number of clusters show that GDPool achieves consistently higher modularity than existing methods while the number of active clusters decreases monotonically with depth. Sensitivity analyses confirm stable behavior across hyperparameter and architectural choices.