How to Bridge Spatial and Temporal Heterogeneity in Link Prediction? A Contrastive Method

TL;DR

This paper introduces CLP, a contrastive learning model that effectively captures spatial and temporal heterogeneity in dynamic networks, significantly improving link prediction accuracy over existing methods.

Contribution

It proposes a novel hierarchical self-supervised architecture that models fine-grained spatial and temporal heterogeneity for link prediction in dynamic networks.

Findings

Outperforms state-of-the-art models with 10.10% AUC improvement

Achieves 13.44% higher AP on real-world datasets

Demonstrates robustness across four diverse datasets

Abstract

Temporal Heterogeneous Networks play a crucial role in capturing the dynamics and heterogeneity inherent in various real-world complex systems, rendering them a noteworthy research avenue for link prediction. However, existing methods fail to capture the fine-grained differential distribution patterns and temporal dynamic characteristics, which we refer to as spatial heterogeneity and temporal heterogeneity. To overcome such limitations, we propose a novel \textbf{C}ontrastive Learning-based \textbf{L}ink \textbf{P}rediction model, \textbf{CLP}, which employs a multi-view hierarchical self-supervised architecture to encode spatial and temporal heterogeneity. Specifically, aiming at spatial heterogeneity, we develop a spatial feature modeling layer to capture the fine-grained topological distribution patterns from node- and edge-level representations, respectively. Furthermore, aiming at temporal heterogeneity, we devise a temporal information modeling layer to perceive the evolutionary dependencies of dynamic graph topologies from time-level representations. Finally, we encode the spatial and temporal distribution heterogeneity from a contrastive learning perspective, enabling a comprehensive self-supervised hierarchical relation modeling for the link prediction task. Extensive experiments conducted on four real-world dynamic heterogeneous network datasets verify that our \mymodel consistently outperforms the state-of-the-art models, demonstrating an average improvement of 10.10\%, 13.44\% in terms of AUC and AP, respectively.