一个基于图卷积神经网络的局部密度优化方法

王浩; 董立岩; 范铁虎; 孙铭会

doi:10.1631/FITEE.1900663

Your Location：

Home >

Browse articles >

一个基于图卷积神经网络的局部密度优化方法

常规文章 | Updated：2022-05-19

- 一个基于图卷积神经网络的局部密度优化方法
- A local density optimization method based on a graph convolutional network
- 信息与电子工程前沿（英文） 2020年21卷第12期页码：1795-1803
- Affiliations：
  
  College of Computer Science and Technology, Jilin University, Changchun 130012, China
  MOE Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Changchun 130012, China
  College of Instrumentation & Electrical Engineering, Jilin University, Changchun 130012, China
- Author bio：
  
  [ "Hao WANG, E-mail: wanghao18@mails.jlu.edu.cn" ]
  [ "Li-yan DONG, E-mail:dongly@jlu.edu.cn" ]
  Tie-hu FAN, E-mail:fth@jlu.edu.cn
  [ "Ming-hui SUN, E-mail:smh@jlu.edu.cn" ]
- Funds：
  
  Project supported by the National Natural Science Foundation of China (Nos. 61272209 and 61872164)
- DOI：10.1631/FITEE.1900663
  中图分类号： TP391
- 收稿：2019-11-30，
  
  修回：2020-;9-24，
  
  纸质出版：2020-12
- Accepted：
Scan QR Code
王浩, 董立岩, 范铁虎, 等. 一个基于图卷积神经网络的局部密度优化方法[J]. 信息与电子工程前沿（英文）, 2020,21(12):1795-1803.

Hao WANG, Li-yan DONG, Tie-hu FAN, et al. A local density optimization method based on a graph convolutional network[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(12): 1795-1803.
王浩, 董立岩, 范铁虎, 等. 一个基于图卷积神经网络的局部密度优化方法[J]. 信息与电子工程前沿（英文）, 2020,21(12):1795-1803. DOI： 10.1631/FITEE.1900663.

Hao WANG, Li-yan DONG, Tie-hu FAN, et al. A local density optimization method based on a graph convolutional network[J]. Frontiers of Information Technology & Electronic Engineering, 2020, 21(12): 1795-1803. DOI： 10.1631/FITEE.1900663.

摘要

基于图卷积神经网络的半监督图分析（GCN）方法已取得成功。然而，该方法忽略了图中节点的某些局部信息，说明GCN数据预处理不够完善，训练产生的模型不够精确。因此，在基于图嵌入技术的多个非监督方法中，对输入数据局部信息的采集非常重要。本文将基于相似邻接度假设的局部分析方法应用到图卷积网络，并给出局部密度的定义；该方法被称作LDGCN。LDGCN通过两种不同方法处理图卷积网络的输入数据，即非平衡方法和平衡方法。被处理后的输入数据包含更详细的结点局部信息，训练所生成的模型更准确。通过GCN原理介绍LDGCN的实现，然后使用3个主流图数据集（Cora，Citeseer和Pubmed）验证其有效性。最后，通过节点分类实验与多个主流图分析方法对比，结果表明LDGCN算法有更好表现。

Abstract

Success has been obtained using a semi-supervised graph analysis method based on a graph convolutional network (GCN). However

GCN ignores some local information at each node in the graph

so that data preprocessing is incomplete and the model generated is not accurate enough. Thus

in the case of numerous unsupervised models based on graph embedding technology

local node information is important. In this paper

we apply a local analysis method based on the similar neighbor hypothesis to a GCN

and propose a local density definition; we call this method LDGCN. The LDGCN algorithm processes the input data of GCN in two methods

i.e.

the unbalanced and balanced methods. Thus

the optimized input data contains detailed local node information

and then the model generated is accurate after training. We also introduce the implementation of the LDGCN algorithm through the principle of GCN

and use three mainstream datasets to verify the effectiveness of the LDGCN algorithm (i.e.

the Cora

Citeseer

and Pubmed datasets). Finally

we compare the performances of several mainstream graph analysis algorithms with that of the LDGCN algorithm. Experimental results show that the LDGCN algorithm has better performance in node classification tasks.

关键词

Keywords

references

HC Chen , , , B Perozzi , , , R Al-Rfou , , , 等 . . A tutorial on network embeddings , , 2018 . . https://arxiv.org/abs/1808.02590v1 https://arxiv.org/abs/1808.02590v1 , , . .

F Fouss , , , A Pirotte , , , JM Renders , , , 等 . . Random-walk computation of similarities between nodes of a graph with application to collaborative recommendation . . IEEE Trans Knowl Data Eng , , 2007 . . 19 ( ( 3 ): ): 355 - - 369 . . DOI: 10.1109/tkde.2007.46 http://doi.org/10.1109/tkde.2007.46 . .

A Grover , , , J Leskovec . . node2vec: scalable feature learning for networks . . Proc 22 nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , , 2016 . . p.855 - - 864 . . DOI: 10.1145/2939672.2939754 http://doi.org/10.1145/2939672.2939754 . .

A Grover , , , A Zweig , , , S Ermon . . Graphite: iterative generative modeling of graphs , , 2018 . . https://arxiv.org/abs/1803.10459v2 https://arxiv.org/abs/1803.10459v2 , , . .

TN Kipf , , , M Welling . . Semi-supervised classification with graph convolutional networks , , 2016 . . https://arxiv.org/abs/1609.02907 https://arxiv.org/abs/1609.02907 , , . .

AN Langville , , , CD Meyer . . Google's PageRank and Beyond: the Science of Search Engine Rankings . . Princeton University Press, Princeton, USA , , 2006 . . p.234 . .

Q Le , , , T Mikolov . . Distributed representations of sentences and documents . . Proc 31 st Int Conf on Machine Learning , , 2014 . . p.Ⅱ-1188 - - Ⅱ-1196 . . . .

Y LeCun , , , B Boser , , , JS Denker , , , 等 . . Backpropagation applied to handwritten zip code recognition . . Neur Comput , , 1989 . . 1 ( ( 4 ): ): 541 - - 551 . . DOI: 10.1162/neco.1989.1.4.541 http://doi.org/10.1162/neco.1989.1.4.541 . .

Y LeCun , , , L Bottou , , , Y Bengio , , , 等 . . Gradient-based learning applied to document recognition . . Proc IEEE , , 1998 . . 86 ( ( 11 ): ): 2278 - - 2324 . . DOI: 10.1109/5.726791 http://doi.org/10.1109/5.726791 . .

Y LeCun , , , Y Bottou , , , G Hinton . . Deep learning . . Nature , , 2015 . . 521 ( ( 7553 ): ): 436 - - 444 . . DOI: 10.1038/nature14539 http://doi.org/10.1038/nature14539 . .

F Lin , , , WW Cohen . . Semi-supervised classification of network data using very few labels . . Int Conf on Advances in Social Networks Analysis and Mining , , 2010 . . p.192 - - 199 . . DOI: 10.1109/ASONAM.2010.19 http://doi.org/10.1109/ASONAM.2010.19 . .

F Lorrain , , , HC White . . Structural equivalence of individuals in social networks . . J Math Soc , , 1971 . . 1 ( ( 1 ): ): 49 - - 80 . . DOI: 10.1080/0022250X.1971.9989788 http://doi.org/10.1080/0022250X.1971.9989788 . .

T Mikolov , , , K Chen , , , G Corrado , , , 等 . . Efficient estimation of word representations in vector space , , 2013 . . https://arxiv.org/abs/1301.3781 https://arxiv.org/abs/1301.3781 , , . .

A Mnih , , , K Kavukcuoglu . . Learning word embeddings efficiently with noise-contrastive estimation . . Proc 26 th Int Conf on Neural Information Processing Systems , , 2013 . . p.2265 - - 2273 . . . .

A Narayanan , , , M Chandramohan , , , LH Chen , , , 等 . . subgraph2vec: learning distributed representations of rooted sub-graphs from large graphs , , 2016 . . https://arxiv.org/abs/1606.08928 https://arxiv.org/abs/1606.08928 , , . .

M Niepert , , , M Ahmed , , , K Kutzkov . . Learning convolutional neural networks for graphs . . Proc 33 rd Int Conf on Machine Learning , , 2016 . . p.2014 - - 2023 . . . .

L Page , , , S Brin , , , R Motwani , , , 等 . . The Pagerank Citation Ranking: Bringing Order to the Web . . Technical Report SIDL-WP-1999-0120, Stanford InfoLab, Stanford, USA , , 1998 . . .

B Perozzi , , , R Al-Rfou , , , S Skiena . . DeepWalk: online learning of social representations . . Proc 20 th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , , 2014 . . p.701 - - 710 . . DOI: 10.1145/2623330.2623732 http://doi.org/10.1145/2623330.2623732 . .

N Pizarro . . Structural identity and equivalence of individuals in social networks: beyond duality . . Int Soc , , 2007 . . 22 ( ( 6 ): ): 767 - - 792 . . DOI: 10.1177/0268580907082260 http://doi.org/10.1177/0268580907082260 . .

LFR Ribeiro , , , PHP Saverese , , , DR Figueiredo . . struc2vec: learning node representations from structural identity . . Proc 23 rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , , 2017 . . p.385 - - 394 . . DOI: 10.1145/3097983.3098061 http://doi.org/10.1145/3097983.3098061 . .

DI Shuman , , , SK Narang , , , P Frossard , , , 等 . . The emerging field of signal processing on graphs: extending high- dimensional data analysis to networks and other irregular domains . . IEEE Signal Process Mag , , 2013 . . 30 ( ( 3 ): ): 83 - - 98 . . DOI: 10.1109/MSP.2012.2235192 http://doi.org/10.1109/MSP.2012.2235192 . .

L Tang , , , H Liu . . Leveraging social media networks for classification . . Data Min Knowl Discov , , 2011 . . 23 ( ( 3 ): ): 447 - - 478 . . DOI: 10.1007/s10618-010-0210-x http://doi.org/10.1007/s10618-010-0210-x . .

HF Wang , , , CY Zhang , , , DY Lin , , , 等 . . An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression . . Front Inform Technol Electron Eng , , 2019 . . 20 ( ( 6 ): ): 816 - - 828 . . DOI: 10.1631/FITEE.1800146 http://doi.org/10.1631/FITEE.1800146 . .

J Weston , , , F Ratle , , , H Mobahi , , , 等 . . Deep learning via semi-supervised embedding . . In: Montavon G, Orr GB, Mȹller KR (Eds.), Neural Networks: Tricks of the Trade. Springer, Berlin, Heidelberg , , 2012 . . p.639 - - 655 . . DOI: 10.1007/978-3-642-35289-8_34 http://doi.org/10.1007/978-3-642-35289-8_34 . .

LM Yang , , , W Zhang , , , YF Chen . . Time-series prediction based on global fuzzy measure in social networks . . Front Inform Technol Electron Eng , , 2015 . . 16 ( ( 10 ): ): 805 - - 816 . . DOI: 10.1631/FITEE.1500025 http://doi.org/10.1631/FITEE.1500025 . .

ZL Yang , , , WW Cohen , , , R Salakhutdinov . . Revisiting semi-supervised learning with graph embeddings . . Proc 33 rd Int Conf on Machine Learning , , 2016 . . p.40 - - 48 . . . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Dynamic prompting class distribution optimization for semi-supervised sound event detection

Interactive medical image segmentation with self-adaptive confidence calibration

NGAT: attention in breadth and depth exploration for semi-supervised graph representation learning

Video summarization with a graph convolutional attention network

Representation learning via a semi-supervised stacked distance autoencoder for image classification