Deep Generative Model for Periodic Graphs
Deep Generative Model for Periodic Graphs
复制标题
DOI：
--
复制
发表时间：
2022-01
期刊：
影响因子：
--
通讯作者：
Shiyu Wang;Xiaojie Guo;Liang Zhao
中科院分区：
文献类型：
--
作者：
Shiyu Wang;Xiaojie Guo;Liang Zhao
周期图是由重复的局部结构组成的图，如晶网和多边形网格。它们的产生式建模在材料设计和图形合成等实际应用中具有很大的潜力。经典模型要么依赖于特定领域的预定义生成原则(例如，在晶体网络设计中)，要么遵循基于几何的规定规则。最近，深度生成模型在自动生成一般图方面显示出巨大的前景。然而，由于以下几个关键挑战：1)保持图的周期性；2)分离局部和全局模式；3)学习重复模式的效率，它们在周期图中的应用还没有得到很好的探索。针对这些问题，本文提出了一种新的周期图深度生成模型--周期图解缠变分自动编码器(PGD-VAE)，该模型能够自动学习、解缠和生成局部和全局图模式。具体地说，我们开发了一种新的周期图编码器，它由全局模式编码器和局部模式编码器组成，确保了表示的全局和局部语义的分离。在此基础上，提出了一种新的周期图译码算法，它由局部结构译码、邻域译码和全局结构译码三部分组成，并给出了保证周期性的输出汇编器。此外，我们设计了一个新的模型学习目标，以帮助确保具有相同局部结构的图的局部语义表示的不变性。为了验证该方法的有效性，我们进行了全面的实验评估。所提出的pgd-vae编码可在https://github.com/shi-yu-wang/PGD-VAE.上获得
Periodic graphs are graphs consisting of repetitive local structures, such as crystal nets and polygon mesh. Their generative modeling has great potential in real-world applications such as material design and graphics synthesis. Classical models either rely on domain-specific predefined generation principles (e.g., in crystal net design), or follow geometry-based prescribed rules. Recently, deep generative models has shown great promise in automatically generating general graphs. However, their advancement into periodic graphs have not been well explored due to several key challenges in 1) maintaining graph periodicity; 2) disentangling local and global patterns; and 3) efficiency in learning repetitive patterns. To address them, this paper proposes Periodical-Graph Disentangled Variational Auto-encoder (PGD-VAE), a new deep generative models for periodic graphs that can automatically learn, disentangle, and generate local and global graph patterns. Specifically, we develop a new periodic graph encoder consisting of global-pattern encoder and local-pattern encoder that ensures to disentangle the representation into global and local semantics. We then propose a new periodic graph decoder consisting of local structure decoder, neighborhood decoder, and global structure decoder, as well as the assembler of their outputs that guarantees periodicity. Moreover, we design a new model learning objective that helps ensure the invariance of local-semantic representations for the graphs with the same local structure. Comprehensive experimental evaluations have been conducted to demonstrate the effectiveness of the proposed method. The code of proposed PGD-VAE is availabe at https://github.com/shi-yu-wang/PGD-VAE.