Fine-Grained Graph Generation through Latent Mixture Scheduling
It addresses the need for fine-grained control over graph properties in applications like drug discovery and social network modeling, offering a method that outperforms recent baselines.
The paper introduces a conditional variational autoencoder with a latent mixture scheduler for fine-grained structural control in graph generation, achieving high generation quality and controllability across five real-world datasets.
Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods that only provide coarse control over graph properties, we introduce a novel conditional variational autoencoder for fine-grained structural control in graph generation. The approach refines the decoder's latent space by dynamically aligning graph- and property-driven representations to improve both graph fidelity and control satisfaction. Specifically, the approach implements a mixture scheduler that progressively integrates graph and control priors. Experiments on five real-world datasets show the efficacy of the proposed model compared to recent baselines, achieving high generation quality while maintaining high controllability.