Structural Deep Network Embedding

Abstract

Networkembeddingisanimportantmethodtolearnlow-dimensional representations of vertexes in networks, aiming to capture and preserve the network structure. Almost all the existing network embeddingmethodsadoptshallowmodels. However,sincetheunderlyingnetworkstructureiscomplex, shallowmodelscannotcapture the highly non-linear network structure, resulting in sub-optimal network representations. Therefore, how to find a method that is able to effectively capture the highly non-linear network structure and preserve the global and local structure is an open yet important problem. To solve this problem, in this paper we propose a StructuralDeepNetworkEmbeddingmethod,namelySDNE.More specifically, we first propose a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non-linear network structure. Then we propose to exploit the first-order and second-order proximity jointly to preserve the network structure. The second-order proximity is used bytheunsupervisedcomponenttocapturetheglobalnetworkstructure. Whilethefirst-orderproximityisusedasthesupervisedinformation in the supervised component to preserve the local network structure. By jointly optimizing them in the semi-supervised deep model, our method can preserve both the local and global network structureandisrobusttosparsenetworks. Empirically,weconduct the experiments on five real-world networks, including a language network, a citation network and three social networks. The results show that compared to the baselines, our method can reconstruct the original network significantly better and achieves substantial gains in three applications, i.e. multi-label classification, link prediction and visualization.