论文标题
全球和本地功能学习用于自我网络分析
Global and Local Feature Learning for Ego-Network Analysis
论文作者
论文摘要
在自我网络中，一个人（自我）以不同的群体（社交界）组织其朋友（改变）。在学习自我及其在低维真实的矢量空间中的变化之后，可以有效地分析该社交网络。然后，通过统计模型轻松利用这些表示形式的任务，例如社交圈检测和预测。通过深度学习的语言建模的最新进展激发了学习网络表示的新方法。这些方法可以捕获网络的全局结构。在本文中，我们进化了这些技术，还编码了社区的局部结构。因此，我们的本地表示捕获了隐藏在大型网络的全局表示中的网络功能。我们表明，社交圈预测的任务受益于我们技术产生的全球和本地特征的组合。
In an ego-network, an individual (ego) organizes its friends (alters) in different groups (social circles). This social network can be efficiently analyzed after learning representations of the ego and its alters in a low-dimensional, real vector space. These representations are then easily exploited via statistical models for tasks such as social circle detection and prediction. Recent advances in language modeling via deep learning have inspired new methods for learning network representations. These methods can capture the global structure of networks. In this paper, we evolve these techniques to also encode the local structure of neighborhoods. Therefore, our local representations capture network features that are hidden in the global representation of large networks. We show that the task of social circle prediction benefits from a combination of global and local features generated by our technique.
