提出自适应图池化方法，自动确定超节点数量
BN-Pool: Bayesian Nonparametric Pooling for Graphs
- 基于贝叶斯非参数框架，动态聚类图节点
- 训练时联合优化任务损失与拓扑重建项
- 避免冗余聚类，适合需要压缩图结构的场景
我们提出 BN-Pool，首个基于聚类的图神经网络池化方法，能自适应确定粗化图中的超节点数量。该方法采用基于贝叶斯非参数框架的生成模型，将图节点划分为无限多个簇。训练过程中，通过结合下游任务的监督损失与无监督辅助项，学习节点到簇的分配；后者鼓励重构原始图拓扑结构，同时惩罚不必要的簇膨胀。通过为每张图自动发现最优粗化层级，BN-Pool 在保持软聚类池化性能的同时，避免了其常见冗余问题，学习出紧凑的池化图。代码已开源：https://github.com/NGMLGroup/Bayesian-Nonparametric-Graph-Pooling。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。