Dynamic Graph Embedding via LSTM History Tracking

TL;DR

This paper introduces a novel dynamic network embedding method that leverages LSTM to incorporate historical node information, enabling efficient and effective analysis of large, evolving networks for tasks like link prediction and anomaly detection.

Contribution

The work presents a new dynamic embedding approach combining static and dynamic node data, using LSTM to track neighbor history, and reduces computational costs by training on temporal walks instead of adjacency matrices.

Findings

Improved performance in anomaly detection, link prediction, and node classification.

Significantly reduced time and memory usage compared to traditional methods.

Effective embedding of large, evolving networks across various domains.

Abstract

Many real world networks are very large and constantly change over time. These dynamic networks exist in various domains such as social networks, traffic networks and biological interactions. To handle large dynamic networks in downstream applications such as link prediction and anomaly detection, it is essential for such networks to be transferred into a low dimensional space. Recently, network embedding, a technique that converts a large graph into a low-dimensional representation, has become increasingly popular due to its strength in preserving the structure of a network. Efficient dynamic network embedding, however, has not yet been fully explored. In this paper, we present a dynamic network embedding method that integrates the history of nodes over time into the current state of nodes. The key contribution of our work is 1) generating dynamic network embedding by combining both dynamic and static node information 2) tracking history of neighbors of nodes using LSTM 3) significantly decreasing the time and memory by training an autoencoder LSTM model using temporal walks rather than adjacency matrices of graphs which are the common practice. We evaluate our method in multiple applications such as anomaly detection, link prediction and node classification in datasets from various domains.