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 2101.09593cs.LGcs.SI
收藏

生成二重图:相似但不同

Generating a Doppelganger Graph: Resembling but Distinct

Emory University(埃默里大学);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室);IBM Research(IBM研究院)

Yuliang Ji, Ru Huang, Jie Chen, Yuanzhe Xi

摘要:

深度生成模型自其诞生以来,已经变得越来越能够生成新颖且感知上真实的信号(例如,图像和声波)。随着图结构数据的深度模型的出现,自然兴趣寻求这些图的生成模型的扩展。最近在从图的集合中学习的情况下看到了成功的扩展(例如,蛋白质数据库),但是从单个图中学习在很大程度上还没有被探索。然而,后一种情况在实践中很重要。例如,金融和医疗系统中的图表包含了如此多的机密信息,以至于公众几乎不可能访问它们,但只有当类似的数据可用于基准测试时,这些领域的开放科学才能取得进展。在这项工作中,我们提出了一种方法来生成一个二重图,类似于一个给定的一个在许多图形属性,但仍然很难被用来逆向工程原来的一个,在这个意义上的一个接近零的边缘重叠。该方法是图表示学习、生成对抗网络和图实现算法的协调。通过与几个图生成模型(无论是否由神经网络参数化)的比较,我们证明了我们的结果几乎没有再现给定的图,但密切匹配其属性。我们进一步表明,下游的任务,如节点分类,对生成的图形达到类似的性能使用原始的。

英文摘要:

Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e.g., images and sound waves). With the emergence of deep models for graph structured data, natural interests seek extensions of these generative models for graphs. Successful extensions were seen recently in the case of learning from a collection of graphs (e.g., protein data banks), but the learning from a single graph has been largely under explored. The latter case, however, is important in practice. For example, graphs in financial and healthcare systems contain so much confidential information that their public accessibility is nearly impossible, but open science in these fields can only advance when similar data are available for benchmarking. In this work, we propose an approach to generating a doppelganger graph that resembles a given one in many graph properties but nonetheless can hardly be used to reverse engineer the original one, in the sense of a near zero edge overlap. The approach is an orchestration of graph representation learning, generative adversarial networks, and graph realization algorithms. Through comparison with several graph generative models (either parameterized by neural networks or not), we demonstrate that our result barely reproduces the given graph but closely matches its properties. We further show that downstream tasks, such as node classification, on the generated graphs reach similar performance to the use of the original ones.

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。

↑