Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space

Abstract

Representation learning over temporal networks has drawn considerable attention in recent years. Efforts are mainly focused on modeling structural dependencies and temporal evolving regularities in Euclidean space which, however, underestimates the inherent complex and hierarchical properties in many real-world temporal networks, leading to sub-optimal embeddings. To explore these properties of a complex temporal network, we propose a hyperbolic temporal graph network (HTGN) that fully takes advantage of the exponential capacity and hierarchical awareness of hyperbolic geometry. More specially, HTGN maps the temporal graph into hyperbolic space, and incorporates hyperbolic graph neural network and hyperbolic gated recurrent neural network, to capture the evolving behaviors and implicitly preserve hierarchical information simultaneously. Furthermore, in the hyperbolic space, we propose two important modules that enable HTGN to successfully model temporal networks: (1) hyperbolic temporal contextual self-attention (HTA) module to attend to historical states and (2) hyperbolic temporal consistency (HTC) module to ensure stability and generalization. Experimental results on multiple real-world datasets demonstrate the superiority of HTGN for temporal graph embedding, as it consistently outperforms competing methods by significant margins in various temporal link prediction tasks. Specifically, HTGN achieves AUC improvement up to 9.98% for link prediction and 11.4% for new link prediction. Moreover, the ablation study further validates the representational ability of hyperbolic geometry and the effectiveness of the proposed HTA and HTC modules.

KDD2021; V2: fixed some typos

References in corpus (3)

• Geometric deep learning: going beyond Euclidean data
• Hyperbolic Geometry of Complex Networks
• The Large Scale Curvature of Networks

Cited by in corpus (12)

• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization
• HICF: Hyperbolic Informative Collaborative Filtering
• DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph
• HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks
• A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
• Network Alignment
• BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
• Predicting Long-term Dynamics of Complex Networks via Identifying Skeleton in Hyperbolic Space
• Dynamic Link Prediction Using Graph Representation Learning with Enhanced Structure and Temporal Information
• Efficient Learning-based Graph Simulation for Temporal Graphs
• Towards Non-Euclidean Foundation Models: Advancing AI Beyond Euclidean Frameworks