On Hierarchical Multi-Resolution Graph Generative Models
This addresses the challenge of data-driven graph generation for domains with inherent hierarchical structures, representing an incremental advancement in graph generative models.
The paper tackles the problem of generating graphs with hierarchical structures by proposing a recursive, multi-resolution generative model that captures community structures at each level, achieving improved generative performance on multiple datasets.
In real world domains, most graphs naturally exhibit a hierarchical structure. However, data-driven graph generation is yet to effectively capture such structures. To address this, we propose a novel approach that recursively generates community structures at multiple resolutions, with the generated structures conforming to training data distribution at each level of the hierarchy. The graphs generation is designed as a sequence of coarse-to-fine generative models allowing for parallel generation of all sub-structures, resulting in a high degree of scalability. Our method demonstrates generative performance improvement on multiple graph datasets.