提出双空间视角的有向图对比学习框架，提升真实网络表示效果。
Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
- 从复域和实域双视角设计扰动与子图增强策略
- 节点分类和链接预测分别提升4.41%和4.34%性能
- 适合处理社交、推荐等有向网络场景
图对比学习（GCL）已成为无需标注信息即可提取图一致表示的强大工具。然而现有方法主要聚焦于无向图，忽视了真实网络中至关重要的方向性信息（如社交网络与推荐系统）。本文提出S2-DiGCL，一个强调复杂域与真实域空间洞察的有向图对比学习新框架。在复域视角下，通过将个性化扰动引入磁拉普拉斯算子，自适应调节边相位与方向语义；在实域视角下，采用基于路径的子图增强策略，捕捉细粒度局部不对称性与拓扑依赖关系。通过联合利用这两个互补的空间视角，S2-DiGCL构建高质量正负样本，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表明，该方法在监督与非监督设置下均达到当前最优性能，节点分类准确率提升4.41%，链接预测性能提升4.34%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。