Hierarchical Discrete Flow Matching for Graph Generation
This addresses computational bottlenecks in graph generation for applications like drug discovery or network analysis, though it appears incremental as it builds on existing denoising-based methods.
The paper tackles the computational inefficiency of denoising-based graph generation models, which suffer from quadratic scaling with node count and many function evaluations, by introducing a hierarchical framework with discrete flow matching. The result is improved graph distribution capture and significantly reduced generation time.
Denoising-based models, including diffusion and flow matching, have led to substantial advances in graph generation. Despite this progress, such models remain constrained by two fundamental limitations: a computational cost that scales quadratically with the number of nodes and a large number of function evaluations required during generation. In this work, we introduce a novel hierarchical generative framework that reduces the number of node pairs that must be evaluated and adopts discrete flow matching to significantly decrease the number of denoising iterations. We empirically demonstrate that our approach more effectively captures graph distributions while substantially reducing generation time.