ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation
ProtoGuide is introduced, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism for discrete diffusion models and raises macro classification accuracy and outperforms DiGress's built-in conditional training under the authors' configuration.
Salvatore Romano, Marco Grassia, Pietro Liò et al.
· 0 citations