论文标题
社交网络潜在空间模型的评论
A Review of Latent Space Models for Social Networks
论文作者
论文摘要
在本文中，我们对社交网络和潜在空间建模的基本面进行了综述。前者讨论了与网络描述有关的重要主题，包括顶点特征和网络结构；后者阐明了网络建模的相关进展，包括随机图模型，广义随机图模型，指数随机图模型和社交空间模型。我们详细讨论了文献中提供的几种潜在空间模型，并在无向的二进制网络的背景下特别关注距离，阶级和特征模型。此外，我们还使用网络文献的二十多个流行数据集，从预测和合适性方面进行经验研究这些模型的行为。
In this paper, we provide a review on both fundamentals of social networks and latent space modeling. The former discusses important topics related to network description, including vertex characteristics and network structure; whereas the latter articulates relevant advances in network modeling, including random graph models, generalized random graph models, exponential random graph models, and social space models. We discuss in detail several latent space models provided in literature, providing special attention to distance, class, and eigen models in the context of undirected, binary networks. In addition, we also examine empirically the behavior of these models in terms of prediction and goodness-of-fit using more than twenty popular datasets of the network literature.
