SCGG: A Deep Structure-Conditioned Graph Generative Model

TL;DR

SCGG is a deep learning model that generates graphs conditioned on a given substructure, enabling targeted graph completion and outperforming existing methods on synthetic and real data.

Contribution

We introduce SCGG, a novel deep graph generative model that conditions on initial subgraphs to generate new nodes and edges autoregressively.

Findings

SCGG outperforms state-of-the-art baselines in graph completion tasks.

The model effectively generates graphs conditioned on structural subgraphs.

Experimental results validate the superiority of SCGG on multiple datasets.

Abstract

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their effectiveness by empowering them to generate new graph samples that meet the desired criteria. This paper presents a conditional deep graph generation method called SCGG that considers a particular type of structural conditions. Specifically, our proposed SCGG model takes an initial subgraph and autoregressively generates new nodes and their corresponding edges on top of the given conditioning substructure. The architecture of SCGG consists of a graph representation learning network and an autoregressive generative model, which is trained end-to-end. Using this model, we can address graph completion, a rampant and inherently difficult problem of recovering missing nodes and their associated edges of partially observed graphs. Experimental results on both synthetic and real-world datasets demonstrate the superiority of our method compared with state-of-the-art baselines.