复杂网络的双曲空间表征学习方法

复杂网络在现实场景中无处不在,高效的复杂网络分析技术具有广泛的应用价值,比如社区检测、链路预测等.然而直接对大规模的复杂网络邻接矩阵进行分析需要较高的时间、空间复杂度,网络表征学习是一种解决此问题的有效方法.该类方法将高维稀疏的网络信息转化为低维稠密的实值向量,可以作为机器学习算法的输入,便于后续应用的高效计算.传统的网络表征学习方法将实体对象嵌入到低维欧氏向量空间中,但复杂网络是一类具有近似树状层次结构、幂率度分布、强聚类特性的网络,该结构更适合用具有负曲率的双曲空间来描述.本文将针对复杂网络的双曲空间表征学习方法进行系统性的介绍和总结.

Hyperbolic Representation Learning for Complex Networks

Complex networks naturally exist in a wide diversity of real-world scenarios. Efficient complex network analysis technology has wide applications, such as community detection, link prediction, etc. However, most complex network analytics suffer the high computation and space cost because of the direct use of large-scale adjacency matrix. Network representation learning is one of the most efficient methods to solve this problem. It converts high-dimensional sparse network information into low-dimensional dense real-valued vector which can be easily exploited by machine learning algorithm. Simultaneously, it facilitates efficient computation for subsequent applications. The traditional network representation embeds the entity objects in the low dimensional Euclidean vector space, but recent work has shown that the appropriate isometric space for embedding complex networks with hierarchical or tree-like structure, power-law degree distributions and high clustering is the negatively curved hyperbolic space. In this survey, we conduct a systematic introduction and review of the literature in hyperbolic representation learning for complex networks.