arXiv:2411.16615cs.LG2024-11
提出基于局部聚类选择的图池化方法，提升图神经网络的压缩效率。
Graph Pooling by Local Cluster Selection
- 通过节点为中心的聚类选择实现图池化
- 在多个基准数据集上优于现有可训练池化方法
- 适合需要高效图压缩的GNN应用
图池化是一类将图作为输入并生成压缩后图作为输出的操作。现代图池化方法具有可训练性，通常作为图神经网络（GNN）架构中的图压缩算子，插入深度处理流程中。本文提出一种新型图池化流程，以及一个以节点为中心的图池化算子，旨在通过局部聚类选择更有效地保留图结构信息。
原文摘要 · Abstract (English)
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.
图神经网络图池化聚类
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。