We introduce the controllable graph generation problem, formulated as controlling graph attributes during the generative process to produce desired graphs with understandable structures. Using a transparent and straightforward Markov model to guide this generative process, practitioners can shape and understand the generated graphs. We propose ${\rm S{\small HADOW}C{\small AST}}$, a generative model capable of controlling graph generation while retaining the original graph's intrinsic properties. The proposed model is based on a conditional generative adversarial network. Given an observed graph and some user-specified Markov model parameters, ${\rm S{\small HADOW}C{\small AST}}$ controls the conditions to generate desired graphs. Comprehensive experiments on three real-world network datasets demonstrate our model's competitive performance in the graph generation task. Furthermore, we show its effective controllability by directing ${\rm S{\small HADOW}C{\small AST}}$ to generate hypothetical scenarios with different graph structures.

翻译：我们引入了可控图形生成问题, 在基因变异过程中, 设计为控制图形属性, 以生成具有可理解结构的所需图形。 使用透明、 直截了当的 Markov 模型来指导该基因变异过程, 执行者可以塑造和理解生成的图形。 我们提议了 $@ rm S= small hadow}C\ small AST ⁇ $, 这是一种能够控制图形生成同时保留原始图形内在属性的基因变异模型。 提议的模型基于一个有条件的基因对抗网络。 观察到的图形和一些用户指定的Markov 模型参数, $_ rm S= sm= Sm sm Som APHOW}C ( 小AST ⁇ $) 控制了生成想要的图形的条件。 对三个真实世界网络数据集的全面实验展示了我们模型在图形生成任务中的竞争性性能。 此外, 我们通过引导 $@ rm S@ smlod hadaw} C\ small AST ⁇ $ 以生成不同图形结构的假设情景来显示其有效控制性 。