Edge-aware Hard Clustering Graph Pooling for Brain Imaging

TL;DR

This paper introduces EHCPool, a novel graph pooling method that incorporates edge features for better brain network analysis using GCNs, improving substructure capture and abnormal brain map identification.

Contribution

The paper proposes a new edge-aware clustering pooling method that redefines graph pooling by integrating edge features and adaptive clustering strategies.

Findings

EHCPool outperforms existing methods on multi-site datasets.

The method effectively captures critical brain substructures.

EHCPool demonstrates robustness and potential for brain network analysis.

Abstract

Graph Convolutional Networks (GCNs) can capture non-Euclidean spatial dependence between different brain regions. The graph pooling operator, a crucial element of GCNs, enhances the representation learning capability and facilitates the acquisition of abnormal brain maps. However, most existing research designs graph pooling operators solely from the perspective of nodes while disregarding the original edge features. This confines graph pooling application scenarios and diminishes its ability to capture critical substructures. In this paper, we propose a novel edge-aware hard clustering graph pool (EHCPool), which is tailored to dominant edge features and redefines the clustering process. EHCPool initially introduced the 'Edge-to-Node' score criterion which utilized edge information to evaluate the significance of nodes. An innovative Iteration n-top strategy was then developed, guided by edge scores, to adaptively learn sparse hard clustering assignments for graphs. Additionally, a N-E Aggregation strategy is designed to aggregate node and edge features in each independent subgraph. Extensive experiments on the multi-site public datasets demonstrate the superiority and robustness of the proposed model. More notably, EHCPool has the potential to probe different types of dysfunctional brain networks from a data-driven perspective. Method code: https://github.com/swfen/EHCPool