论文标题
深图生成器：调查
Deep Graph Generators: A Survey
论文作者
论文摘要
在过去的几年中，深层生成模型在图像，语音和自然语言处理等领域取得了巨大的成功。得益于基于图的深度学习的进步，特别是图形表示学习，最近出现了深度的图生成方法，从发现新颖的分子结构到建模社交网络的新应用程序。本文对基于深度学习的图生成方法进行了全面的调查，并将其分为五个广泛类别，即基于自动码器，基于RL，基于RL的，对抗性和基于流程的图形生成器，为读者提供了每个类中这些方法的详细描述。我们还介绍了公开可用的源代码，常用的数据集以及最广泛使用的评估指标。最后，我们强调了现有的挑战并讨论未来的研究方向。
Deep generative models have achieved great success in areas such as image, speech, and natural language processing in the past few years. Thanks to the advances in graph-based deep learning, and in particular graph representation learning, deep graph generation methods have recently emerged with new applications ranging from discovering novel molecular structures to modeling social networks. This paper conducts a comprehensive survey on deep learning-based graph generation approaches and classifies them into five broad categories, namely, autoregressive, autoencoder-based, RL-based, adversarial, and flow-based graph generators, providing the readers a detailed description of the methods in each class. We also present publicly available source codes, commonly used datasets, and the most widely utilized evaluation metrics. Finally, we highlight the existing challenges and discuss future research directions.
