arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.15544cs.LGcs.AIcs.SI
收藏

深度图生成器综述

Deep Graph Generators: A Survey

Sharif University of Technology(谢里夫理工大学);Amirkabir University of Technology(阿米尔卡比尔理工大学)

Faezeh Faez, Yassaman Ommi, Mahdieh Soleymani Baghshah, Hamid R. Rabiee

摘要:

过去几年,深度生成模型在图像、语音和自然语言处理等领域取得了巨大成功。由于基于图的深度学习的进步,特别是图表示学习,深度图生成方法最近出现了新的应用,从发现新的分子结构到建模社交网络。本文对基于深度学习的图形生成方法进行了全面的调查,并将其分为五大类,即自回归,基于自编码器,基于RL,对抗和基于流的图形生成器,为读者提供了每类方法的详细描述。我们还提供了公开的源代码,常用的数据集和最广泛使用的评估指标。最后,我们强调了现有的挑战,并讨论了未来的研究方向。

英文摘要:

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.

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。

↑