dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning

TL;DR

dyngraph2vec is a deep learning model that captures the evolution of dynamic graphs to improve link prediction accuracy in evolving networks.

Contribution

The paper introduces dyngraph2vec, a novel deep architecture that models temporal network dynamics for enhanced link prediction in dynamic graphs.

Findings

dyngraph2vec outperforms existing methods on real datasets.

Model effectively captures network evolution.

Improves link prediction accuracy.

Abstract

Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need of capturing dynamics for prediction on a toy data set created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real world data sets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction.