EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
This addresses the need for predicting changes in dynamic networks, which is crucial for applications in graph mining, but it appears incremental as it builds on existing graph neural network and recurrent methods.
The paper tackles the problem of predicting the evolution of dynamic graphs, which is significant in graph mining but underexplored, and proposes a model using graph neural networks and recurrent architectures to predict graph topology at future time steps, showing effectiveness on artificial and real-world datasets.
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.