基于嵌套生成对抗学习的网络嵌入

Network Embedding Based on Nested Generative Adversarial Networks

当前网络嵌入研究更多关注信息网络结构和结点之间一阶或高阶近似关系,对于网络结点自身属性考虑较少.本文提出一种嵌套的生成对抗网络模型N-GAN(Nesting Generative Adversarial Networks for Network Embed⁃ding),实现了网络结构和节点属性同时嵌入到低维向量,从而最大程度保存原始高维信息网络特征.N-GAN模型设计灵活,具有很好的延伸性和扩张性,并在真实数据上验证了N-GAN的性能及其稳定性,其嵌入的低维表示在不同应用中表现出不错的性能.

The current network embedding researches focus more on the information network structure and first-or⁃der or higher-order approximation of nodes,but less on the attributes of network nodes.This paper proposes a nested genera⁃tive adversarial network model N-GAN(Nesting Generative Adversarial Networks for Network Embedding),which embeds the network structure and nodes'attributes into the low-dimensional vector at the same time,so as to preserve the feature of the original high-dimensional information network maximumly.N-GAN model is flexible in design and has good extensibil⁃ity and expansibility.The performance and stability of N-GAN model are verified on real datasets.The embedded low-di⁃mensional representation of N-GAN model shows good performance in different tasks.