AUTHOR=Tan Qiaoyu , Liu Ninghao , Hu Xia 

TITLE=Deep Representation Learning for Social Network Analysis

JOURNAL=Frontiers in Big Data

VOLUME=Volume 2 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2019.00002

DOI=10.3389/fdata.2019.00002

ISSN=2624-909X

ABSTRACT=Social network analysis is an important problem in data mining. A fundamental step for analyzing3social networks is to encode network data into low-dimensional representations, i.e., network4embeddings,  so that the network topology structure and other attribute information can be5effectively preserved. Network representation leaning facilitates further applications such as6classification, link prediction, anomaly detection and clustering. In addition, techniques based on7deep neural networks have attracted great interests over the past a few years. In this survey, we8conduct a comprehensive review of current literature in network representation learning utilizing9neural network models. First, we introduce the basic models for learning node representations in10homogeneous networks. Meanwhile, we will also introduce some extensions of the base models11in tackling more complex scenarios,  such as analyzing attributed networks,  heterogeneous12networks and dynamic networks. Then, we introduce the techniques for embedding subgraphs.13After that, we present the applications of network representation learning. At the end, we discuss14some promising research directions for future work