Dynamic Graph Representation Learning via Self-Attention Networks
This addresses the challenge of modeling temporal changes in graphs for applications like link prediction, but it is incremental as it extends self-attention methods to dynamic graphs.
The paper tackles the problem of learning node representations in dynamic graphs, which evolve over time, by proposing Dynamic Self-Attention Network (DySAT), and it achieves significant performance gains over state-of-the-art baselines in link prediction experiments on communication and bipartite rating networks.
Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evolve over time. In this paper, we present Dynamic Self-Attention Network (DySAT), a novel neural architecture that operates on dynamic graphs and learns node representations that capture both structural properties and temporal evolutionary patterns. Specifically, DySAT computes node representations by jointly employing self-attention layers along two dimensions: structural neighborhood and temporal dynamics. We conduct link prediction experiments on two classes of graphs: communication networks and bipartite rating networks. Our experimental results show that DySAT has a significant performance gain over several different state-of-the-art graph embedding baselines.