BN-Pool: Bayesian Nonparametric Pooling for Graphs
Not on the map. Why?
Abstract (arXiv)
We introduce BN-Pool, the first clustering-based pooling method for Graph Neural Networks that adaptively determines the number of supernodes in a coarsened graph. BN-Pool leverages a generative model based on a Bayesian nonparametric framework for partitioning graph nodes into an unbounded number of clusters. During training, the node-to-cluster assignments are learned by combining the supervised loss of the downstream task with an unsupervised auxiliary term, which encourages the reconstruction of the original graph topology while penalizing unnecessary proliferation of clusters. By automatically discovering the optimal coarsening level for each graph, BN-Pool preserves the performance of soft-clustering pooling methods while avoiding their typical redundancy by learning compact pooled graphs. The code is available at https://github.com/NGMLGroup/Bayesian-Nonparametric-Graph-Pooling.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 16 Jan 2025.
Builds on
47 of 70 references.
References · 47
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
- 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
- 2019Strategies for Pre-training Graph Neural Networkscited by 971
- 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
- 2015Generating Sentences from a Continuous Spacecited by 612
35 more
- 2019Graph U-Netscited by 492
- 2019Self-Attention Graph Poolingcited by 421
- 2016Ladder Variational Autoencoderscited by 318
- 2022Long Range Graph Benchmarkcited by 263
- 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
- 2020Graph Clustering with Graph Neural Networkscited by 163
- 2019ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representationscited by 156
- 2021Graph Condensation for Graph Neural Networkscited by 150
- 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
- 2019Graph Convolutional Networks with EigenPoolingcited by 94
- 2018Implicit Reparameterization Gradientscited by 85
- 2021Understanding Pooling in Graph Neural Networkscited by 69
- 2022Structural Entropy Guided Graph Hierarchical Poolingcited by 62
- 2020Memory-Based Graph Networkscited by 56
- 2019Edge Contraction Pooling for Graph Neural Networkscited by 53
- 2016Stick-Breaking Variational Autoencoderscited by 44
- 2020Topology-Aware Graph Pooling Networkscited by 44
- 2019Dirichlet Variational Autoencodercited by 43
- 2020Dirichlet Graph Variational Autoencodercited by 40
- 2019Stochastic Blockmodels meet Graph Neural Networkscited by 39
- 2018Pathwise Derivatives Beyond the Reparameterization Trickcited by 36
- 2020Path Integral Based Convolution and Pooling for Graph Neural Networkscited by 35
- 2023The expressive power of pooling in Graph Neural Networkscited by 35
- 2019Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Poolingcited by 30
- 2020Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoderscited by 30
- 2022Higher-order Clustering and Pooling for Graph Neural Networkscited by 26
- 2019iPool -- Information-based Pooling in Hierarchical Graph Neural Networkscited by 21
- 2023Graph-based Time Series Clustering for End-to-End Hierarchical Forecastingcited by 17
- 2024Graph-based Forecasting with Missing Data through Spatiotemporal Downsamplingcited by 17
- 2021Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learningcited by 15
- 2021Graph Pooling via Coarsened Graph Infomaxcited by 15
- 2021Pyramidal Reservoir Graph Neural Networkcited by 10
- 2022Simplifying Clustering with Graph Neural Networkscited by 8
- 2024A Comprehensive Graph Pooling Benchmark: Effectiveness, Robustness and Generalizabilitycited by 7
- 2024MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networkscited by 5
Built on by
Citing papers per year: 2025: 2.
2 papers.