DCMSL: Dual influenced community strength-boosted multi-scale graph contrastive learning
Abstract: Highlights•Defined dual influenced community strength by topology and node attributes to measure node cruciality.•Developed graph data augmentation methods for attributes and edges based on node cruciality.•Proposed multi-scale graph contrastive loss with primary and auxiliary components for node and community learning.•Achieved state-of-the-art performance three downstream tasks, highlighting the effectiveness of method.
Loading