Modularity-based representation learning for networks

doi:10.1088/1674-1056/abbbec

Abstract Network embedding aims at learning low-dimensional representation of vertexes in a network and effectively preserving network structures. These representations can be used as features for many complex tasks on networks such as community detection and multi-label classification. Some classic methods based on the skip-gram model have been proposed to learn the representation of vertexes. However, these methods do not consider the global structure ( i.e., community structure) while sampling vertex sequences in network. To solve this problem, we suggest a novel sampling method which takes community information into consideration. It first samples dense vertex sequences by taking advantage of modularity function and then learns vertex representation by using the skip-gram model. Experimental results on the tasks of community detection and multi-label classification show that our method outperforms three state-of-the-art methods on learning the vertex representations in networks.

Keywords: network embedding low-dimensional representation vertex sequences community detection

Received: 17 July 2020
Revised: 31 August 2020
Accepted manuscript online: 28 September 2020

PACS:	89.75.Hc	(Networks and genealogical trees)
	89.75.-k	(Complex systems)
	64.60.aq	(Networks)

Fund: Project supported by the National Natural Science Foundation of China (Grant No. 61673085), the Program from the Sichuan Provincial Science and Technology, China (Grant No. 2018RZ0081), and the Fundamental Research Funds of China West Normal University (Grant No. 17E063).

Corresponding Authors: ^†Corresponding author. E-mail: hejialin32@126.com

Cite this article:

Jialin He(何嘉林), Dongmei Li(李冬梅), and Yuexi Liu(刘阅希) Modularity-based representation learning for networks 2020 Chin. Phys. B 29 128901

[1] Sun H L, Ch'ng E, Yong X, Garibaldi J M, See S and Chen D B Physica A 496 108-120 https://www.sciencedirect.com/science/article/abs/pii/S03784371173134812018
[2] He J L,Chen D B Physica A 429 87-94 https://www.sciencedirect.com/science/article/abs/pii/S03784371150019222015
[3] Tang L and Liu H Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, June 28-July 1, 2009, Paris, France, p. 817 https://dl.acm.org/doi/abs/10.1145/1557019.15571092009
[4] Tang L,Liu H Proceedings of the 18th ACM Conference on Information and Knowledge Management, November 2-6, 2009, Hong Kong, China, p. 1107 https://dl.acm.org/doi/abs/10.1145/1645953.16460942009
[5] Xie Y, Gong M, Qin A K, Tang Z and Fan X Inf. Sci. 504 20 https://www.sciencedirect.com/science/article/pii/S00200255193064252019
[6] Gao Y, Gong M, Xie Y and Zhong H Knowl Based Syst 193 105418 https://www.sciencedirect.com/science/article/abs/pii/S09507051193065132020
[7] Perozzi B, Al-Rfou R and Skiena S Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 24-27, 2014, New York, USA, p. 701 https://dl.acm.org/doi/abs/10.1145/2623330.26237322014
[8] Grover A,Leskovec J Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 24-27, 2016, San Francisco, USA, p. 855 https://dl.acm.org/doi/abs/10.1145/2939672.29397542016
[9] Tang J, Qu M, Wang M, Zhang M, Yan J and Mei Q Proceedings of the 24th International Conference on World Wide Web, May 18-22, 2015, Florence, Italy, p. 1067 https://dl.acm.org/doi/abs/10.1145/2736277.27410932015
[10] Cao S, Lu W and Xu Q Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 12-17, 2016, Phoenix, USA, p. 1145 https://www.researchgate.net/profile/ShaoshengCao/publication/303495864deepneuralnetworkforlearninggraphrepresentations/links/5d1b1c7ea6fdcc2462b75011/deep-neural-network-for-learning-graph-representations.pdf2016
[11] Feng R, Yang Y, Hu W, Wu F and Zhuang Y Proceedings of the 32th AAAI Conference on Artificial Intelligence, February 2-7, 2018, New Orleans, USA, p. 282 https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/165582018
[12] Wang D, Cui P and Zhu W Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 24-27, 2016, San Francisco, USA, p. 1225 https://dl.acm.org/doi/abs/10.1145/2939672.29397532016
[13] Yanardag P and Vishwanathan S V N 2015 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 23-27, 2015, New York, USA, p. 1365 https://dl.acm.org/doi/abs/10.1145/2783258.2783417
[14] Wang X, Cui P, Wang J, Pei J, Zhu W and Yang S Proceedings of the 31 AAAI Conference on Artificial Intelligence, February 4-9, 2017, San Francisco,USA, p. 203 http://119.28.72.117/papers/NE-Community.pdf2017
[15] Tu C, Zeng X, Wang H, Zhang Z, Liu Z, Sun M and Lin L IEEE Trans. Knowl. Data Eng. 311051 https://ieeexplore.ieee.org/abstract/document/84032932018
[16] Chen H, Perozzi B, Hu Y and Skiena S Proceedings of the 32th AAAI Conference on Artificial Intelligence, Feburary 2-7, 2018, New Orleans,USA, p. 2127 https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/162732017
[17] Armand pour M, Ding P, Huang J and Hu X Proceedings of the 33th AAAI Conference on Artificial Intelligence, January 27-February 1, 2019, Hawaii, USA, p. 3191 https://www.aaai.org/ojs/index.php/AAAI/article/view/41872019
[19] Cheng Y IEEE Trans. Pattern Anal. Mach. Intell. 17 790-799 https://ieeexplore.ieee.org/abstract/document/400568/1995
[20] Arthur D and Vassilvitskii S sergei/papers/kMeansPP-soda.pdf2007 Proceedings of the 18th Annual ACM-SIAM Symposium on Discrete Algorithms, January 7-9, 2007, New Orleans,USA, p. 1027 http://theory.stanford.edu/
[21] Danon L, Diaz-Guilera A, Duch J and Arenas A J. Stat. Mech. Theory Exp. 2005, p. P09008 https://iopscience.iop.org/article/10.1088/1742-5468/2005/09/P09008/meta2005
[22] Tsoumakas G and Vlahavas I Machine Learning: ECML 2007 (Berlin: Springer-Verlag) p. 406 https://link.springer.com/chapter/10.1007/978-3-540-74958-538#citeas2007
[23] Radicchi F, Castellano C, Cecconi F, Loreto V and Parisi D Proc. Natl. Acad. Sci. USA 1012658 https://www.pnas.org/content/101/9/2658.short2004
[24] Newman M E and Girvan M Phys. Rev. E 69 026113 https://journals.aps.org/pre/abstract/10.1103/PhysRevE.69.0261132004
[25] Zachary W W J. Anthropol. Res. 33 452 https://www.journals.uchicago.edu/doi/abs/10.1086/jar.33.4.36297521977
[26] Girvan M and Newman M E Proc. Natl. Acad. Sci. USA 997821 https://www.pnas.org/content/99/12/7821.short2002
[27] Lusseau D, Schneider K, Boisseau O J, Haase P, Slooten E and Dawson S M Behav. Ecol. Sociobiol. 54 396 https://link.springer.com/article/10.1007/s00265-003-0651-y2003
[28] Rossi R and Ahmed N Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25-30, 2015, Austin, USA, p. 777 http://ryanrossi.com/pubs/aaai15-nr.pdf2015
[29] Lancichinetti A, Fortunato S and Radicchi F Phys. Rev. E 78 046110 https://journals.aps.org/pre/abstract/10.1103/PhysRevE.78.0461102008
[30] Fan R E, Chang K W, Hsieh C J, Wang X R and Lin C J J. Mach. Learn. Res. 91871 https://www.jmlr.org/papers/v9/fan08a.html2008
[31] Perozzi B, Kulkarni V, Chen H and Skiena S Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, July 31-August 3, 2017, Sydney, Australia, p. 258 https://dl.acm.org/doi/abs/10.1145/3110025.31100862017
[32] Sen P, Namata G, Bilgic M, Getoor L, Galligher B and Eliassi-Rad T AI Mag. 29 93 https://www.aaai.org/ojs/index.php/aimagazine/article/view/21572008

[1]	Pitman-Yor process mixture model for community structure exploration considering latent interaction patterns Jing Wang(王晶) and Kan Li(李侃). Chin. Phys. B, 2021, 30(12): 120518.
[2]	Community detection in signed networks based on discrete-time model Jianrui Chen(陈建芮), Li Zhang(张莉), Weiwei Liu(刘维维), Zaizai Yan(闫在在). Chin. Phys. B, 2017, 26(1): 018901.
[3]	Detecting overlapping communities in networks via dominant label propagation Sun He-Li (孙鹤立), Huang Jian-Bin (黄健斌), Tian Yong-Qiang (田勇强), Song Qin-Bao (宋擒豹), Liu Huai-Liang (刘怀亮). Chin. Phys. B, 2015, 24(1): 018703.
[4]	Detecting community structure using label propagation with consensus weight in complex network Liang Zong-Wen (梁宗文), Li Jian-Ping (李建平), Yang Fan (杨帆), Athina Petropulu. Chin. Phys. B, 2014, 23(9): 098902.
[5]	Dynamic evolutionary community detection algorithms based on the modularity matrix Chen Jian-Rui (陈建芮), Hong Zhi-Min (洪志敏), Wang Li-Na (汪丽娜), Wu Lan (乌兰). Chin. Phys. B, 2014, 23(11): 118903.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Modularity-based representation learning for networks

Cite this article:

Online attention