Graph Generation with Variational Recurrent Neural Network
This addresses graph generation for applications requiring synthetic graph data, but appears incremental as it builds on existing variational and recurrent approaches.
The paper tackles the challenging problem of generating graph structures with complex dependencies by introducing GraphVRNN, a probabilistic autoregressive model that captures joint distributions of graph structures and node attributes. Experimental results show the variational component enables modeling of complicated distributions and generation of plausible structures and attributes.
Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes. In this paper, we introduce Graph Variational Recurrent Neural Network (GraphVRNN), a probabilistic autoregressive model for graph generation. Through modeling the latent variables of graph data, GraphVRNN can capture the joint distributions of graph structures and the underlying node attributes. We conduct experiments on the proposed GraphVRNN in both graph structure learning and attribute generation tasks. The evaluation results show that the variational component allows our network to model complicated distributions, as well as generate plausible structures and node attributes.