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.

翻译：图对比学习（Graph Contrastive Learning, GCL）已成为一种无需标签信息即可从图中提取一致表示的有效工具。然而，现有方法主要关注无向图，忽略了在实际网络（如社交网络和推荐系统）中至关重要且不可或缺的方向信息。本文提出S2-DiGCL——一种新颖框架，强调从复杂域和实域空间视角进行有向图对比学习。在复杂域视角下，S2-DiGCL向磁拉普拉斯矩阵引入个性化扰动，以自适应地调节边相位和方向语义；在实域视角下，它采用基于路径的子图增强策略，捕捉细粒度的局部非对称性和拓扑依赖性。通过联合利用这两种互补的空间视角，S2-DiGCL构建了高质量的正负样本，从而实现更通用且鲁棒的有向图对比学习。在7个真实世界有向图数据集上的大量实验证明了本方法的优越性：在监督和无监督设置下，节点分类性能提升4.41%，链接预测性能提升4.34%，均达到当前最优水平。