Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball

2026-09-04

AI Summary

本文提出了一种新的图池化方法TPAGP，通过结合节点特征和拓扑信息动态划分图，生成多粒度表示，有效捕捉局部和全局结构模式。

Abstract

Graph pooling aims to compress the graph, including both node embeddings and their underlying topological patterns, into a more compact representation. Previous works focus primarily on the overly fine-grained representation of nodes, progressively coarsening the graph by removing nodes or merging them into clusters, thus neglecting the global-to-local patterns and adaptive granularity of the graph's topological structure. In the real scenario, graphs as a whole can be considered the coarsest level of granularity, encapsulating the global topological structure, with progressively finer-grained local topological structures represented from top to bottom. This process continues until the adaptive granularity for each subdomain is reached. To this end, we propose a novel Topology-Preserving Adaptive Graph Pooling (TPAGP) method that dynamically partitions graphs into granular balls by integrating node features and topological information, enabling the generation of multi-granularity representations that effectively capture both local and global structural patterns. Additionally, we design a multi-granularity graph network model that facilitates feature interaction and optimization across different granularities, significantly enhancing performance in graph classification tasks. Experimental results demonstrate that TPAGP outperforms existing pooling methods across various benchmark datasets, effectively mitigating information loss caused by fixed-granularity strategies.

Problem

• graph pooling
• topological structure
• global-to-local patterns
• adaptive granularity
• node embeddings

Innovation

• Topology-Preserving Adaptive Graph Pooling
• Granular-Ball
• Multi-Granularity Representation
• Feature Interaction
• Graph Classification