.png){kind=icon}
Return
Enhancing graph learning interpretability through modulating cluster information flow
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.113178.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Interpretable graph learning is essential for scientific applications that depend on learning models to extract reliable insights from graph-structured data. Recent efforts to explain GNN predictions focus on identifying vital substructures, such as subgraphs. However, existing approaches tend to misclassify the neighboring irrelevant nodes as part of the vital subgraphs. To address this, we propose Cluster Information Flow Graph Neural Networks (CIFlow-GNN), a built-in model-level method that provides accurate interpretable subgraph explanations by modulating the cluster information flow. CIFlow-GNN incorporates two modules, i.e., the graph clustering module and the cluster prototype module. The graph clustering module partitions the nodes according to their connectivity in the graph topology and their similarity in cluster features. Specifically, we introduce a cluster feature loss to regulate information flow at the cluster level. We prove that the proposed cluster feature loss is a lower bound of the InfoNCE loss. Optimizing the cluster feature loss reduces the mutual information among clusters and achieves the modulation of cluster information flow. Subsequently, the graph prototype module uses prototypes as a bridge to select important clusters as vital subgraphs by integrating information across all graphs. To ensure accurate correspondence between clusters and prototypes, we further modulate the cluster information flow at the prototype level. Experimental studies on both synthetic and real-world datasets demonstrate that our proposed CIFlow-GNN can identify vital subgraphs effectively and efficiently.
Keywords:
graph neural networks
interpretable machine learning
cluster information flow
subgraph explanation
graph clustering
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
View more organizations
Cited Papers
ShareSaveMolecular substructure graph attention network for molecular property identification in drug discovery.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveSelf-attention empowered graph convolutional network for structure learning and node embeddingPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAIShareSaveStructured self-attention architecture for graph-level representation learningPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSave
Incorporating global and local social networks for group recommendationsPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSave View more