arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.03545cs.SIcs.LG
收藏

基于GAN的图拓扑特征学习

Learning Graph Topological Features via GAN

University of Electronic Science and Technology of China(中国电子科技大学);IBM Watson Research Center(IBM沃森研究中心);Columbia University(哥伦比亚大学);Boston University(波士顿大学)

Weiyi Liu, Hal Cooper, Min Hwan Oh, Sailung Yeung, Pin-Yu Chen, Toyotaro Suzumura, Lingli Chen

摘要:

受图像领域生成对抗网络(GANs)生成能力的启发,我们引入了一种新的分层架构,用于通过GANs从单个任意输入图中学习特征拓扑特征。由多个GANs组成的分层架构保留了局部和全局拓扑特征,并自动将输入图划分为代表性阶段以进行特征学习。这些阶段有助于重建,并可用作相关拓扑结构重要性的指标。实验表明,我们的方法产生的子图保留了广泛的拓扑特征,即使在早期重建阶段(不像一个单一的GAN,它不能很容易地识别这些功能,更不用说重建原始图)。本文是将GANs与图拓扑分析相结合的研究。

英文摘要:

Inspired by the generation power of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs. The hierarchical architecture consisting of multiple GANs preserves both local and global topological features and automatically partitions the input graph into representative stages for feature learning. The stages facilitate reconstruction and can be used as indicators of the importance of the associated topological structures. Experiments show that our method produces subgraphs retaining a wide range of topological features, even in early reconstruction stages (unlike a single GAN, which cannot easily identify such features, let alone reconstruct the original graph). This paper is firstline research on combining the use of GANs and graph topological analysis.

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。

↑