提出一种通过局部全局正则化实现层次图池化的新方法
LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation
- 基于期望最大化框架，用正则化对齐不同尺度的局部与全局信息
- 在多个图分类基准上表现略优于基线模型
- 适合需要多尺度图分析的研究者使用
层次图池化（HGP）旨在解决传统图神经网络（GNN）固有的扁平性及缺乏多尺度建模的问题。然而，多数HGP方法不仅忽视图的全局拓扑结构，过度关注特征学习，且未能对齐局部与全局特征，而图分析本质上应是多尺度的。本文提出LGRPool，一种基于机器学习期望最大化框架的HGP方法，通过正则化机制，使不同层级的表示中局部消息传递与全局拓扑信息保持一致。实验结果表明，该方法在若干图分类基准上表现略优于部分基线模型。
原文摘要 · Abstract (English)
Hierarchical graph pooling(HGP) are designed to consider the fact that conventional graph neural networks(GNN) are inherently flat and are also not multiscale. However, most HGP methods suffer not only from lack of considering global topology of the graph and focusing on the feature learning aspect, but also they do not align local and global features since graphs should inherently be analyzed in a multiscale way. LGRPool is proposed in the present paper as a HGP in the framework of expectation maximization in machine learning that aligns local and global aspects of message passing with each other using a regularizer to force the global topological information to be inline with the local message passing at different scales through the representations at different layers of HGP. Experimental results on some graph classification benchmarks show that it slightly outperforms some baselines.
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。