Embedding Dynamic Attributed Networks by Modeling the Evolution Processes

TL;DR

This paper introduces a high-order spatio-temporal embedding model for dynamic attributed networks, effectively capturing their evolution over time and outperforming existing methods in link prediction and node classification tasks.

Contribution

The paper proposes a novel activeness-aware neighborhood embedding and an attention-based prediction framework for dynamic network embedding, avoiding RNNs for better efficiency and flexibility.

Findings

Outperforms baseline methods in dynamic link prediction

Achieves higher accuracy in node classification

Effectively models network evolution over time

Abstract

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embedding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real-world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks.