DynGEM: Deep Embedding Method for Dynamic Graphs

TL;DR

DynGEM is a deep autoencoder-based algorithm designed for efficient, stable, and scalable embedding of evolving dynamic graphs, outperforming static methods in various graph analysis tasks.

Contribution

It introduces DynGEM, a novel deep autoencoder approach that effectively embeds dynamic graphs with improved stability and efficiency over existing static methods.

Findings

DynGEM achieves superior stability in dynamic graph embeddings.

It handles growing graphs efficiently over time.

Experimental results show better scalability and performance in multiple tasks.

Abstract

Embedding large graphs in low dimensional spaces has recently attracted significant interest due to its wide applications such as graph visualization, link prediction and node classification. Existing methods focus on computing the embedding for static graphs. However, many graphs in practical applications are dynamic and evolve constantly over time. Naively applying existing embedding algorithms to each snapshot of dynamic graphs independently usually leads to unsatisfactory performance in terms of stability, flexibility and efficiency. In this work, we present an efficient algorithm DynGEM based on recent advances in deep autoencoders for graph embeddings, to address this problem. The major advantages of DynGEM include: (1) the embedding is stable over time, (2) it can handle growing dynamic graphs, and (3) it has better running time than using static embedding methods on each snapshot of a dynamic graph. We test DynGEM on a variety of tasks including graph visualization, graph reconstruction, link prediction and anomaly detection (on both synthetic and real datasets). Experimental results demonstrate the superior stability and scalability of our approach.