Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
This work addresses a gap in graph contrastive learning for directed graphs, which is crucial for applications like social networks and recommendations, though it is incremental as it builds on existing undirected graph methods.
The paper tackles the problem of extending graph contrastive learning to directed graphs by proposing S2-DiGCL, a framework that uses dual spatial perspectives to incorporate directional information, resulting in state-of-the-art performance with improvements of 4.41% in node classification and 4.34% in link prediction on real-world datasets.
Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information. However, existing methods predominantly focus on undirected graphs, disregarding the pivotal directional information that is fundamental and indispensable in real-world networks (e.g., social networks and recommendations).In this paper, we introduce S2-DiGCL, a novel framework that emphasizes spatial insights from complex and real domain perspectives for directed graph (digraph) contrastive learning. From the complex-domain perspective, S2-DiGCL introduces personalized perturbations into the magnetic Laplacian to adaptively modulate edge phases and directional semantics. From the real-domain perspective, it employs a path-based subgraph augmentation strategy to capture fine-grained local asymmetries and topological dependencies. By jointly leveraging these two complementary spatial views, S2-DiGCL constructs high-quality positive and negative samples, leading to more general and robust digraph contrastive learning. Extensive experiments on 7 real-world digraph datasets demonstrate the superiority of our approach, achieving SOTA performance with 4.41% improvement in node classification and 4.34% in link prediction under both supervised and unsupervised settings.