arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.00449cs.LG
收藏

GrannGAN:图注释生成对抗网络

GrannGAN: Graph annotation generative adversarial networks

University of Geneva(日内瓦大学);Geneva School for Business administration HES-SO(HES-SO日内瓦商学院);Center for Artificial Intelligence and Robotics (CAIRO), FHWS(维尔茨堡-施韦因富特应用技术大学人工智能与机器人中心(CAIRO))

Yoann Boget, Magda Gregorova, Alexandros Kalousis

摘要:

我们考虑的问题,高维分布建模和生成新的例子的数据与复杂的关系特征结构一致的图形骨架。我们提出的模型通过将任务分成两个阶段来解决生成受每个数据点的特定图结构约束的数据特征的问题。在第一个模型中,与给定图的节点相关联的特征的分布,在第二个模型中,它有条件地补充节点特征上的边特征。我们遵循隐式分布建模的策略,通过生成对抗网络(GAN)结合置换等变消息传递架构,在节点和边缘的集合上操作。这使得能够一次性(在2个阶段中)生成所有图对象的特征向量,而不是缓慢得多的顺序模型的一个接一个的生成,防止了对基于可能性的生成模型通常需要的昂贵的图匹配过程的需要,并且通过对图表示中的特定节点排序不敏感来有效地使用网络容量。据我们所知,这是第一个方法,模型的特征分布沿图骨架,允许代用户指定的结构的注释图。我们的实验证明了我们的模型通过对三个带注释的图数据集进行定量评估来学习复杂结构化分布的能力。

英文摘要:

We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features. We follow the strategy of implicit distribution modelling via generative adversarial network (GAN) combined with permutation equivariant message passing architecture operating over the sets of nodes and edges. This enables generating the feature vectors of all the graph objects in one go (in 2 phases) as opposed to a much slower one-by-one generations of sequential models, prevents the need for expensive graph matching procedures usually needed for likelihood-based generative models, and uses efficiently the network capacity by being insensitive to the particular node ordering in the graph representation. To the best of our knowledge, this is the first method that models the feature distribution along the graph skeleton allowing for generations of annotated graphs with user specified structures. Our experiments demonstrate the ability of our model to learn complex structured distributions through quantitative evaluation over three annotated graph datasets.

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。

↑