SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation

TL;DR

SeaDAG introduces a semi-autoregressive diffusion model for conditional DAG generation, maintaining full graph structure at each step and enabling property control, which improves the realism and alignment of generated graphs with specified conditions.

Contribution

The paper presents a novel semi-autoregressive diffusion approach for conditional DAG generation that preserves full graph structure and incorporates property conditioning during training.

Findings

Effective generation of realistic DAGs for circuits and molecules

Enhanced property control in DAG generation

High-quality DAGs closely matching given conditions

Abstract

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.