用菱形铺砌聚类提升几何图神经网络的几何特征捕捉能力
Rhomboid Tiling for Geometric Graph Deep Learning
- 基于菱形铺砌结构设计新型聚类方法，挖掘数据复杂几何信息
- 在7个基准数据集上超越21种先进模型，实现最优图分类性能
- 适合处理具有丰富几何结构的图数据，如分子、3D点云等
图神经网络（GNN）通过基于邻域的消息传递框架，在图结构数据学习中表现出色。许多层次化图聚类池化方法通过引入聚类策略改进该框架，构建更具表达力的模型。然而，这些方法严重依赖图的连接结构，难以捕捉几何图中固有的丰富几何特征。为此，我们提出菱形铺砌（Rhomboid Tiling, RT）聚类，一种基于菱形铺砌结构的新型聚类方法，利用数据的复杂几何信息，有效提取其高阶几何结构。此外，我们设计了基于RT聚类的层次化图聚类池化模型RTPool，用于图分类任务。所提模型在全部7个基准数据集上均优于21种先进方法。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have proven effective for learning from graph-structured data through their neighborhood-based message passing framework. Many hierarchical graph clustering pooling methods modify this framework by introducing clustering-based strategies, enabling the construction of more expressive and powerful models. However, all of these message passing framework heavily rely on the connectivity structure of graphs, limiting their ability to capture the rich geometric features inherent in geometric graphs. To address this, we propose Rhomboid Tiling (RT) clustering, a novel clustering method based on the rhomboid tiling structure, which performs clustering by leveraging the complex geometric information of the data and effectively extracts its higher-order geometric structures. Moreover, we design RTPool, a hierarchical graph clustering pooling model based on RT clustering for graph classification tasks. The proposed model demonstrates superior performance, outperforming 21 state-of-the-art competitors on all the 7 benchmark datasets.
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。