SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation
This addresses the challenge of generating precise DAG structures for applications such as circuit design and molecular synthesis, representing an incremental improvement over existing methods.
The paper tackled the problem of conditional generation of Directed Acyclic Graphs (DAGs) by introducing SeaDAG, a semi-autoregressive diffusion model that maintains a complete graph structure at each step, resulting in high-quality and realistic DAGs aligned with specified properties in tasks like circuit and molecule generation.
We introduce SeaDAG, a semi-autoregressive diffusion model for conditional generation of Directed Acyclic Graphs (DAGs). Considering their inherent layer-wise structure, we simulate layer-wise autoregressive generation by designing different denoising speed for different layers. Unlike conventional autoregressive generation that lacks a global graph structure view, our method maintains a complete graph structure at each diffusion step, enabling operations such as property control that require the full graph structure. Leveraging this capability, we evaluate the DAG properties during training by employing a graph property decoder. We explicitly train the model to learn graph conditioning with a condition loss, which enhances the diffusion model's capacity to generate graphs that are both realistic and aligned with specified properties. We evaluate our method on two representative conditional DAG generation tasks: (1) circuit generation from truth tables, where precise DAG structures are crucial for realizing circuit functionality, and (2) molecule generation based on quantum properties. Our approach demonstrates promising results, generating high-quality and realistic DAGs that closely align with given conditions.