EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs

Changmin Wu, Giannis Nikolentzos, Michalis Vazirgiannis

TL;DR: Combining graph neural networks and the RNN graph generative model, we propose a novel architecture that is able to learn from a sequence of evolving graphs and predict the graph topology evolution for the future timesteps

Abstract:

Neural networks for structured data like graphs have been studied extensively in recent years.
To date, the bulk of research activity has focused mainly on static graphs.
However, most real-world networks are dynamic since their topology tends to change over time.
Predicting the evolution of dynamic graphs is a task of high significance in the area of graph mining.
Despite its practical importance, the task has not been explored in depth so far, mainly due to its challenging nature.
In this paper, we propose a model that predicts the evolution of dynamic graphs.
Specifically, we use a graph neural network along with a recurrent architecture to capture the temporal evolution patterns of dynamic graphs.
Then, we employ a generative model which predicts the topology of the graph at the next time step and constructs a graph instance that corresponds to that topology.
We evaluate the proposed model on several artificial datasets following common network evolving dynamics, as well as on real-world datasets.
Results demonstrate the effectiveness of the proposed model.

Keywords: temporal graphs, graph neural network, graph generative model, graph topology prediction