Dynamic Joint Variational Graph Autoencoders

TL;DR

This paper introduces Dyn-VGAE, a novel framework for learning dynamic network representations by capturing both local structures and temporal evolution, outperforming static graph embedding methods.

Contribution

It proposes a joint learning framework for dynamic graph embeddings that simultaneously captures local structures and temporal dependencies across snapshots.

Findings

Effective in modeling dynamic networks

Outperforms static embedding methods

Captures temporal evolution successfully

Abstract

Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dynamic networks and evolve over time. Most existing graph embedding algorithms were developed for static graphs mainly and cannot capture the evolution of a large dynamic network. In this paper, we propose Dynamic joint Variational Graph Autoencoders (Dyn-VGAE) that can learn both local structures and temporal evolutionary patterns in a dynamic network. Dyn-VGAE provides a joint learning framework for computing temporal representations of all graph snapshots simultaneously. Each auto-encoder embeds a graph snapshot based on its local structure and can also learn temporal dependencies by collaborating with other autoencoders. We conduct experimental studies on dynamic real-world graph datasets and the results demonstrate the effectiveness of the proposed method.