Structural Deep Embedding for Hyper-Networks
Structural Deep Embedding for Hyper-Networks
复制标题
DOI：
10.1609/aaai.v32i1.11266
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Ke Tu;Peng Cui;Xiao Wang;Fei Wang;Wenwu Zhu
中科院分区：
文献类型：
--
作者：
Ke Tu;Peng Cui;Xiao Wang;Fei Wang;Wenwu Zhu
网络嵌入是近年来数据挖掘领域的研究热点。现有的网络嵌入方法主要集中在具有成对关系的网络上。然而，在真实的世界中，数据点之间的关系可以超越成对，即，在由超边表示的每个关系中涉及三个或更多个对象，从而形成超网络。当超边是不可分解的，即一个超边中的任何节点子集都不能形成另一个超边时，这些超网络对现有的网络嵌入方法提出了很大的挑战。这些不可分解的超边在异构网络中特别常见。在本文中，我们提出了一种新的深度超网络嵌入（DHNE）模型嵌入超网络与不可分解的超边。更具体地说，我们从理论上证明了现有方法中常用的嵌入空间中的任何线性相似性度量都不能保持超网络中的不可分解性，因此提出了一种新的深度模型来实现非线性元组相似性函数，同时保持所形成的嵌入空间中的局部和全局邻近性。我们对四种不同类型的超网络进行了广泛的实验，包括GPS网络，在线社交网络，药物网络和语义网络。实证结果表明，我们的方法可以显着和一贯优于国家的最先进的算法。
Network embedding has recently attracted lots of attentions in data mining. Existing network embedding methods mainly focus on networks with pairwise relationships. In real world, however, the relationships among data points could go beyond pairwise, i.e., three or more objects are involved in each relationship represented by a hyperedge, thus forming hyper-networks. These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge. These indecomposable hyperedges are especially common in heterogeneous networks. In this paper, we propose a novel Deep Hyper-Network Embedding (DHNE) model to embed hyper-networks with indecomposable hyperedges. More specifically, we theoretically prove that any linear similarity metric in embedding space commonly used in existing methods cannot maintain the indecomposibility property in hyper-networks, and thus propose a new deep model to realize a non-linear tuplewise similarity function while preserving both local and global proximities in the formed embedding space. We conduct extensive experiments on four different types of hyper-networks, including a GPS network, an online social network, a drug network and a semantic network. The empirical results demonstrate that our method can significantly and consistently outperform the state-of-the-art algorithms.