From Graphs to Feeders: Constraint-Guided Diffusion for Rule-Compliant Feeder Generation
The proposed PG-DiGress model injects feeder constraints into the reverse diffusion process through soft masks that suppress incompatible edge classes during denoising, followed by a final projection step that rebuilds a connected, rule-compliant feeder graph.
Yu-Yao Qin, Andrew Glaws, Aadil Latif et al.
· 0 citations