Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding. Generating such graphs enables tasks such as simulation, data augmentation and novel instance discovery; however, directed graph generation remains underexplored. We identify two key factors limiting progress in this direction: first, modeling edge directionality introduces a substantially larger dependency space, making the underlying distribution harder to learn; second, the absence of standardized benchmarks hinders rigorous evaluation. Addressing the former requires more expressive models that are sensitive to directional topologies. We propose Directo, the first generative model for directed graphs built upon the discrete flow matching framework. Our approach combines: (i) principled positional encodings tailored to asymmetric pairwise relations, (ii) a dual-attention mechanism capturing both incoming and outgoing dependencies, and (iii) a robust, discrete generative framework. To support evaluation, we introduce a benchmark suite covering synthetic and real-world datasets. It shows that our method performs strongly across diverse settings and even competes with specialized models for particular classes, such as directed acyclic graphs. Our results highlight the effectiveness and generality of our approach, establishing a solid foundation for future research in directed graph generation.

翻译：有向图天然地建模具有非对称有序关系的系统，这对于生物学、交通运输、社会网络及视觉理解等应用至关重要。生成此类图可实现仿真、数据增强及新实例发现等任务；然而，有向图生成的研究仍显不足。我们识别出限制该方向进展的两个关键因素：首先，建模边方向性引入了显著更大的依赖空间，使得底层分布更难学习；其次，标准化基准的缺失阻碍了严谨的评估。针对前者需要能够敏感捕捉方向拓扑的更具表达力的模型。我们提出了Directo，首个基于离散流匹配框架构建的有向图生成模型。我们的方法结合了：(i) 针对非对称成对关系设计的原理性位置编码，(ii) 同时捕捉入向与出向依赖的双重注意力机制，以及(iii) 一个鲁棒的离散生成框架。为支持评估，我们引入了一个涵盖合成与真实数据集的基准测试集。实验表明，我们的方法在多样化的设定下均表现优异，甚至可与针对特定类别（如有向无环图）的专用模型相竞争。我们的结果凸显了该方法的有效性与通用性，为未来有向图生成研究奠定了坚实基础。