Graph Pooling by Local Cluster Selection

Yizhu Chen

Graph Pooling by Local Cluster Selection

Machine Learning 2024-12-05 v2

Authors: Yizhu Chen

Abstract

Graph pooling is a family of operations which take graphs as input and produce shrinked graphs as output. Modern graph pooling methods are trainable and, in general inserted in Graph Neural Networks (GNNs) architectures as graph shrinking operators along the (deep) processing pipeline. This work proposes a novel procedure for pooling graphs, along with a node-centred graph pooling operator.

Keywords

graph clustering graph neural network graph generation

Cite

@article{arxiv.2411.16615,
  title  = {Graph Pooling by Local Cluster Selection},
  author = {Yizhu Chen},
  journal= {arXiv preprint arXiv:2411.16615},
  year   = {2024}
}

Comments

11 pages, 4 figures

Related papers

View all related →