Structure-guided attributed network embedding with “centroid” enhancement

被引:0
作者
Zihan Liao
Wenxin Liang
Beilei Cui
Xin Liu
机构
[1] Dalian University of Technology,School of Software
[2] National Institute of Advanced Industrial Science and Technology (AIST),Data Platform Research Team, Artificial Intelligence Research Center (AIRC)
来源
Computing | 2021年 / 103卷
关键词
Attributed network; Network embedding; Node classification; Node clustering; Social networks; 68T07; 68R10;
D O I
暂无
中图分类号
学科分类号
摘要
Attributed network embedding aims at learning low-dimensional network representations in terms of both network structure and attribute information. Most existing methods deal with network structure and attributes separately and combine them in particular ways, which weaken the affinity between structure and attributes and thus lead to suboptimal performance. Moreover, some methods focus solely on local or global network structure, without fully utilizing the structure information underling the network. To address these limitations, we propose structure-guided attributed network embedding with “centroid” enhancement, an unsupervised approach to embed network structure and attribute information comprehensively and seamlessly. Specifically, we regard the neighborhood of each node as a “cluster” and calculate a “centroid” for it through graph convolutional network. We design a “centroid”-based triplet regularizer to impose a gap constraint inspired by K-means. A “centroid”-augment skip-gram model is utilized to deal with high-order proximity. By jointly optimizing the two objectives, the learned representation can preserve both local-global network structure and attribute information. Throughout the model, we exploit network structure to guide the aggregation of attributes, and thus effectively captures the affinity between them. Experimental results on eight real-world datasets demonstrate the superiority of our model over the state-of-the-art methods.
引用
收藏
页码:1599 / 1620
页数:21
相关论文
共 37 条
  • [1] Belkin M(2003)Laplacian eigenmaps for dimensionality reduction and data representation Neural Comput 15 1373-1396
  • [2] Niyogi P(2018)A survey on network embedding IEEE Trans Knowl Data Eng 31 833-852
  • [3] Cui P(2008)Visualizing data using t-sne J Mach Learn Res 9 2579-2605
  • [4] Wang X(2000)Nonlinear dimensionality reduction by locally linear embedding Science 290 2323-2326
  • [5] Pei J(2008)Collective classification in network data AI Mag 29 93-106
  • [6] Zhu W(2000)A global geometric framework for nonlinear dimensionality reduction Science 290 2319-2323
  • [7] Maaten L(2019)Inter-intra information preserving attributed network embedding IEEE Access 7 79463-79476
  • [8] Hinton G(2019)Attributed network embedding via subspace discovery Data Min Knowl Disc 33 1953-1980
  • [9] Roweis ST(2018)Anrl: Attributed network representation learning via deep neural networks IJCAI 18 3155-3161
  • [10] Saul LK(undefined)undefined undefined undefined undefined-undefined