arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.17341cs.LG
收藏

结构约束图的生成建模

Generative Modelling of Structurally Constrained Graphs

EPFL(洛桑联邦理工学院)

Manuel Madeira, Clement Vignac, Dorina Thanou, Pascal Frossard

AI总结:

针对图扩散模型难以整合领域知识导致生成无效图的问题,提出ConStruct框架,通过边缘吸收噪声模型和投影算子确保采样图全程满足平面性等硬约束,在合成及真实数据集上性能领先,如数字病理数据中数据有效性提升达71.1个百分点。

摘要:

图扩散模型已成为图生成领域的最先进技术;然而,将领域知识整合到这些模型中仍然具有挑战性。在现实场景中,领域知识尤为重要,因为生成的无效图会阻碍其在实际应用中的部署。无约束和条件图扩散模型无法保证此类特定领域的结构特性。我们提出了ConStruct(结构约束图生成框架),这是一种新颖的框架,可使图扩散模型纳入对特定特性(如平面性或无环性)的硬约束。我们的方法确保在正向和反向过程的整个轨迹中,采样图始终处于满足指定特性的图域内。这是通过引入边缘吸收噪声模型和新的投影算子实现的。ConStruct在多种结构约束和边缘删除不变约束中表现出通用性,并在合成基准和属性化真实世界数据集上均实现了最先进的性能。例如,通过在数字病理学图数据集中纳入平面性约束,所提出的方法优于现有基线,将数据有效性提高了高达71.1个百分点。

英文摘要:

Graph diffusion models have emerged as state-of-the-art techniques in graph generation; yet, integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where invalid generated graphs hinder deployment in practical applications. Unconstrained and conditioned graph diffusion models fail to guarantee such domain-specific structural properties. We present ConStruct, a novel framework that enables graph diffusion models to incorporate hard constraints on specific properties, such as planarity or acyclicity. Our approach ensures that the sampled graphs remain within the domain of graphs that satisfy the specified property throughout the entire trajectory in both the forward and reverse processes. This is achieved by introducing an edge-absorbing noise model and a new projector operator. ConStruct demonstrates versatility across several structural and edge-deletion invariant constraints and achieves state-of-the-art performance for both synthetic benchmarks and attributed real-world datasets. For example, by incorporating planarity constraints in digital pathology graph datasets, the proposed method outperforms existing baselines, improving data validity by up to 71.1 percentage points.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑