[1]张蕾,钱峰,赵姝,等.基于多粒度结构的网络表示学习[J].智能系统学报,2019,14(06):1233-1242.[doi:10.11992/tis.201905045]
 ZHANG Lei,QIAN Feng,ZHAO Shu,et al.Network representation learning based on multi-granularity structure[J].CAAI Transactions on Intelligent Systems,2019,14(06):1233-1242.[doi:10.11992/tis.201905045]
点击复制

基于多粒度结构的网络表示学习(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年06期
页码:
1233-1242
栏目:
出版日期:
2019-11-05

文章信息/Info

Title:
Network representation learning based on multi-granularity structure
作者:
张蕾12 钱峰12 赵姝1 陈洁1 张燕平1 刘峰1
1. 安徽大学 计算机科学与技术学院, 安徽 合肥 230601;
2. 铜陵学院 数学与计算机学院, 安徽 铜陵 244061
Author(s):
ZHANG Lei12 QIAN Feng12 ZHAO Shu1 CHEN Jie1 ZHANG Yanping1 LIU Feng1
1. School of Computer Science and Technology, Anhui University, Hefei 230601, China;
2. School of Mathematics and Computer Science, Tongling University, Tongling 244061, China
关键词:
网络表示学习网络拓扑模块度增量网络粒化多粒度结构图卷积网络节点分类链接预测
Keywords:
network represent learningnetwork topologymodularity incrementnetwork coarseningmulti-granularity structureGraph Convolution Networknode classificationlink prediction
分类号:
TN929.12
DOI:
10.11992/tis.201905045
摘要:
图卷积网络(GCN)能够适应不同结构的图,但多数基于GCN的方法难以有效地捕获网络的高阶相似性。简单添加卷积层将导致输出特征过度平滑并使它们难以区分,而且深层神经网络更难训练。本文选择将网络的多粒度结构和图卷积网络结合起来用于学习网络的节点特征表示,提出基于多粒度结构的网络表示学习方法Multi-GS。首先,基于模块度聚类和粒计算思想,用分层递阶的多粒度空间替代原始的单层网络拓扑空间;然后,利用GCN模型学习不同粗细粒度空间中粒的表示;最后,由粗到细将不同粒的表示组合为原始空间中节点的表示。实验结果表明:Multi-GS能够捕获多种结构信息,包括一阶和二阶相似性、社团内相似性(高阶结构)和社团间相似性(全局结构)。在绝大多数情况下,使用多粒度的结构可改善节点分类任务的分类效果。
Abstract:
The Graph Convolution Network (GCN) can adapt to graphs with different structures. However, most GCN-based models have difficulty effectively capturing the high-order similarity of the network. Simply adding a convolution layer will cause the output features to be too smooth and difficult to distinguish. Moreover, the deep neural network is more difficult to train. In this paper, multi-granularity structure and a GCN are combined to represent the node characteristics of the learning network. A multi-granularity structure-based network representation learning method, Multi-GS, is proposed. First, based on the idea of modularity clustering and granular computing, hierarchical multi-granularity space was used to replace the original single-layer network topology space. The GCN model was then used to learn the representation of granules in different coarse- and fine-granularity spaces. Finally, representations of the different grains were combined into representations of nodes in the original space from coarse to fine. Experimental results showed that multi-GS can capture a variety of structural information, including first-order and second-order similarity, intra-community similarity (high-order structure), and inter-community similarity (global structure). In most cases, using multi-granularity structure can improve the classification performance of node classification tasks.

参考文献/References:

[1] 涂存超, 杨成, 刘知远, 等. 网络表示学习综述[J]. 中国科学:信息科学, 2017, 47(8):980-996 TU Cunchao, YANG Cheng, LIU Zhiyuan, et al. Network representation learning:an overview[J]. Scientia sinica informationis, 2017, 47(8):980-996
[2] SHEIKH N, KEFATO Z T, MONTRESOR M. Semi-supervised heterogeneous information network embedding for node classification using 1D-CNN[C]//Proceedings of the Fifth International Conference on Social Networks Analysis, Management and Security. Valencia, Spain, 2018:177-181.
[3] XU Guangluan, WANG Xiaoke, WANG Yang, et al. Edge-nodes representation neural machine for link prediction[J]. Algorithms, 2019, 12(1):12.
[4] HU Xuegang, HE Wei, LI Lei, et al. An efficient and fast algorithm for community detection based on node role analysis[J]. International journal of machine learning and cybernetics, 2019, 10(4):641-654.
[5] PEREDA M, ESTRADA E. Visualization and machine learning analysis of complex networks in hyperspherical space[J]. Pattern recognition, 2019, 86:320-331.
[6] SHI Chuan, HU Binbin, ZHAO W X, et al. Heterogeneous information network embedding for recommendation[J]. IEEE transactions on knowledge and data engineering, 2019, 31(2):357-370.
[7] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA, 2014:701-710.
[8] GROVER A, LESKOVEC J. node2vec:Scalable feature learning for networks[C]//Proceedings of the 22th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, USA, 2016:855-864.
[9] CAO Shaosheng, LU Wei, XU Qiongkai. GraRep:learning graph representations with global structural information[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. Melbourne, Australia, 2015:891-900.
[10] PEROZZI B, KULKARNI V, CHEN Haochen, et al. Don’t walk, Skip!:Online learning of multi-scale network embeddings[C]//Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017. Sydney, Australia, 2017:258-265.
[11] CAO Shaosheng, LU Wei, XU Qiongkai. Deep neural networks for learning graph representations[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix, USA, 2016:1145-1152.
[12] RIBEIRO L F R, SAVERESE P H P, FIGUEIREDO D R. struc2vec:Learning node representations from structural identity[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax, Canada, 2017:385-394.
[13] WANG Xiao, CUI Peng, WANG Jing, et al. Community preserving network embedding[C]//Proceedings of the 31th AAAI Conference on Artificial Intelligence. San Francisco, California, USA, 2017:203-209.
[14] 方莲娣, 张燕平, 陈洁, 等. 基于三支决策的非重叠社团划分[J]. 智能系统学报, 2017, 12(3):293-300 FANG Liandi, ZHANG Yanping, CHEN Jie, et al. Three-way decision based on non-overlapping community division[J]. CAAI transactions on intelligent systems, 2017, 12(3):293-300
[15] DONNAT C, ZITNIK M, HALLAC D, et al. Learning structural node embeddings via diffusion wavelets[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London, UK, 2018:1320-1329.
[16] CHEN Haochen, PEROZZI B, HU Hifan, et al. HARP:hierarchical representation learning for networks[C]//Proceedings of the 32th AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA, 2018:2127-2134.
[17] ZHANG Si, TONG Hanghang, XU Jiejun, et al. Graph convolutional networks:algorithms, applications and open challenges[C]//Proceedings of the 7th International Conference on Computational Data and Social Networks. Shanghai, China, 2018:79-91.
[18] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C/OL].[2019-01-28]. https://arxiv.org/pdf/1609.02907.pdf.
[19] LI Qimai, HAN Zhichao, WU Xiaoming. Deeper insights into graph convolutional networks for semi-supervised learning[C]//Proceedings of the 32th AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA, 2018:3538-3545.
[20] 张燕平, 张铃, 吴涛. 不同粒度世界的描述法——商空间法[J]. 计算机学报, 2004, 27(3):328-333 ZHANG Yanping, ZHANG Ling, WU Tao. The representation of different granular worlds:a quotient space[J]. Chinese journal of computers, 2004, 27(3):328-333
[21] 赵姝, 柯望, 陈洁, 等. 基于聚类粒化的社团发现算法[J]. 计算机应用, 2014, 34(10):2812-2815 ZHAO Shu, KE Wang, CHEN Jie, et al. Community detection algorithm based on clustering granulation[J]. Journal of computer applications, 2014, 34(10):2812-2815
[22] NEWMAN M E J. Fast algorithm for detecting community structure in networks[J]. Physical review E, 2003, 69(6):066133.
[23] 赵姝, 赵晖, 陈洁, 等. 基于社团结构的多粒度结构洞占据者发现及分析[J]. 智能系统学报, 2016, 11(3):343-351 ZHAO Shu, ZHAO Hui, CHEN Jie, et al. Recognition and analysis of structural hole spanner in multi-granularity based on community structure[J]. CAAI transactions on intelligent systems, 2016, 11(3):343-351
[24] KIPF T N, WELLING M. Variational graph auto-encoders[C/OL].[2019-01-28]. https://arxiv.org/pdf/1611.07308.pdf.
[25] MCCALLUM A K, NIGAM K, RENNIE J, et al. Automating the construction of internet portals with machine learning[J]. Information retrieval, 2000, 3(2):127-163.
[26] BREITKREUTZ B J, STARK C, REGULY T, et al. The BioGRID interaction database:2008 update[J]. Nucleic acids research, 2008, 36:D637-D640.
[27] GAO Hongchang, HUANG Heng. Self-paced network embedding[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. London, UK, 2018:1406-1415.
[28] TANG Lei, LIU Huan. Relational learning via latent social dimensions[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Paris, France, 2009:817-826.
[29] FAWCETT T. An introduction to ROC analysis[J]. Pattern recognition letters, 2006, 27(8):861-874.
[30] FAHAD A, ALSHATRI N, TARI Z, et al. A survey of clustering algorithms for big data:Taxonomy and empirical analysis[J]. IEEE transactions on emerging topics in computing, 2014, 2(3):267-279.

相似文献/References:

[1]常亮,张伟涛,古天龙,等.知识图谱的推荐系统综述[J].智能系统学报,2019,14(02):207.[doi:10.11992/tis.201805001]
 CHANG Liang,ZHANG Weitao,GU Tianlong,et al.Review of recommendation systems based on knowledge graph[J].CAAI Transactions on Intelligent Systems,2019,14(06):207.[doi:10.11992/tis.201805001]
[2]张潇鲲,刘琰,陈静.引入外部词向量的文本信息网络表示学习[J].智能系统学报,2019,14(05):1056.[doi:10.11992/tis.201809037]
 ZHANG Xiaokun,LIU Yan,CHEN Jing.Representation learning using network embedding based on external word vectors[J].CAAI Transactions on Intelligent Systems,2019,14(06):1056.[doi:10.11992/tis.201809037]

备注/Memo

备注/Memo:
收稿日期:2019-05-23。
基金项目:国家自然科学基金项目(61876001,61602003,61673020);中国国防科技创新区规划项目(2017-0001-863015-0009);国家重点研究与发展项目(2017YFB1401903);安徽省自然科学基金项目(1508085MF113,1708085QF156).
作者简介:张蕾,女,1980年生,讲师,主要研究方向为数据挖掘、网络表示学习;钱峰,男,1978年生,讲师,主要研究方向为数据挖掘、网络表示学习;赵姝,女,1979年生,教授,博士生导师,博士,安徽省人工智能学会常务理事,安徽省计算机学会理事,中国人工智能学会粒计算与知识发现专委会委员,CIPS社会媒体处理专委会委员,主要研究方向为机器学习、粒计算以及社交网络分析和科技大数据挖掘应用研究。获得发明专利和软件著作权多项,发表学术论文60余篇。
通讯作者:赵姝.E-mail:zhaoshuzs2002@hotmail.com
更新日期/Last Update: 2019-12-25