Toward General Digraph Contrastive Learning: A Dual Spatial Perspective

2025-10-17

AI Summary

Existing graph contrastive learning methods primarily target undirected graphs and struggle to model the critical directional structures inherent in directed graphs. To address this, we propose S2-DiGCL—the first directed graph contrastive learning framework integrating dual perspectives in complex and real vector spaces. Its key contributions are: (1) complex-domain perturbation grounded in the magnetic Laplacian operator, coupled with adaptive edge-phase modulation, to explicitly encode directed adjacency relationships; and (2) a path-guided subgraph augmentation strategy that captures local asymmetry and higher-order topological dependencies. Evaluated on seven real-world directed graph benchmarks, S2-DiGCL achieves state-of-the-art performance—yielding average improvements of 4.41% in node classification and 4.34% in link prediction—while remaining compatible with both supervised and unsupervised settings.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Extracting representations from directed graphs with directional information
• Adapting graph contrastive learning to handle edge directionality
• Improving node classification and link prediction in digraphs

Innovation

• Uses magnetic Laplacian with personalized perturbations
• Employs path-based subgraph augmentation strategy
• Leverages dual spatial views for digraph contrastive learning