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

by   Menglin Yang, et al.

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 prediction. Moreover, the ablation study further validates the representational ability of hyperbolic geometry and the effectiveness of the proposed HTA and HTC modules.


page 1

page 2

page 3

page 4


HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction

Temporal link prediction, aiming to predict future edges between paired ...

Enhancing Hyperbolic Graph Embeddings via Contrastive Learning

Recently, hyperbolic space has risen as a promising alternative for semi...

H2TNE: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces

Temporal heterogeneous information network (temporal HIN) embedding, aim...

Time-aware Hyperbolic Graph Attention Network for Session-based Recommendation

Session-based Recommendation (SBR) is to predict users' next interested ...

Hyperbolic Curvature Graph Neural Network

Hyperbolic space is emerging as a promising learning space for represent...

Hyperbolic Representation Learning: Revisiting and Advancing

The non-Euclidean geometry of hyperbolic spaces has recently garnered co...

Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

Learning representations for graphs plays a critical role in a wide spec...

Please sign up or login with your details

Forgot password? Click here to reset