Network Representation Learning

logo

Lab of Media and Network

Department of Computer Science & Technology

Tsinghua University

Hierarchical Taxonomy Aware Network Embedding

J Ma, P Cui, X Wang, W Zhu. KDD 2018

NetHiex is a network embedding algorithm that preserves the hierarchical structure of the embedding space. It learns node embeddings while uncovering the underlying hierarchical taxonomy in an unsupervised manner.

Motivation

Network embedding learns the low-dimensional representations for vertices, while preserving the inter-vertex similarity reflected by the network structure. The neighborhood structure of a vertex is usually closely related with an underlying hierarchical taxonomy--he vertices are associated with successively broader categories that can be organized hierarchically. The categories of different levels reflects similarity of different granularity. The hierarchy of the taxonomy therefore requires that the learned representations support multiple levels of granularity. Moreover, the hierarchical taxonomy enables the information to flow between vertices via their common categories, and thus provides an effective mechanism for alleviating data scarcity. However, incorporating the hierarchical taxonomy into network embedding poses a great challenge (since the taxonomy is generally unknown), and it is neglected by the existing approaches. In this paper, we propose NetHiex, a NETwork embedding model that captures the latent HIErarchical taXonomy. In our model, a vertex representation consists of multiple components that are associated with categories of different granularity. The representations of both the vertices and the categories are co-regularized. We employ the nested Chinese restaurant process to guide the search of the most plausible hierarchical taxonomy. The network structure is then recovered from the latent representations via a Bernoulli distribution. The whole model is unified within a nonparametric probabilistic framework. A scalable expectation-maximization algorithm is derived for optimization. Empirical results demonstrate that NetHiex achieves significant performance gain over the state-of-arts.

framework

Code

Source Code: nethiex-linux.zip

Slides: slides

Poster: poster

References

Hierarchical Taxonomy Aware Network Embedding

Jianxin Ma, Peng Cui, Xiao Wang, Wenwu Zhu. KDD 2018.