Abstract
Granular computing (GrC) as a problem-solving concept and new information processing paradigm is deeply rooted in human thinking, which has attracted many researchers to study it theoretically, and has gradually applied to data-driven problems. Network embedding, as known as network representation learning, aiming to map nodes in network into a low-dimensional representation, is a data-driven problem. Most existing methods are based on a single granular, which learn representations from local structure of nodes. But global structure is important information on the network and has been proven to facilitate several network analysis tasks. Therefore, how to introduce GrC into network embedding to obtain a multi-granular network representation that preserves the global and local structure of nodes is a meaningful and tough task. In this paper, we introduce Quotient Space Theory, one of the GrC theories into network embedding and propose a Multi-Granular Network Representation Learning method based on Quotient Space Theory (MG_NRL, for short), which can preserve global and local structure at different granularities. Firstly, we granulate the network repeatedly to obtain a multi-granular network. Secondly, the embedding of the coarsest network is computed using any existing embedding method. Finally, the network representation of each granular layer is learned by recursively refining method from the coarsest network to original network. Experimental results on multi-label classification task demonstrate that MG_NRL significantly outperforms other state-of-the-art methods.
Similar content being viewed by others
References
Bargiela A, Pedrycz W (2008) Toward a theory of granular computing for human-centered information processing. IEEE Trans Fuzzy Syst 16(2):320–330
Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Social network data analytics, Springer, New York, pp 115–148
Blondel VD, Guillaume JL, Lambiotte R, Lefebvre E (2008) Fast unfolding of communities in large networks. J Stat Mech Theory Exp 10:155–168
Chen H, Perozzi B, Hu Y, Skiena S (2018) Harp: hierarchical representation learning for networks. In: 32th AAAI conference on artificial intelligence
Clauset A, Moore C, Newman ME (2008) Hierarchical structure and the prediction of missing links in networks. Nature 453(7191):98–101
Correa CD, Ma KL (2011) Visualizing social networks. In: Social network data analytics, Springer, New York, pp 307–326
Ding CH, He X, Zha H, Gu M, Simon HD (2001) A min-max cut algorithm for graph partitioning and data clustering. In: Proceedings 2001 IEEE international conference on data mining, IEEE, pp 107–114
Fan RE, Chang KW, Hsieh CJ, Wang XR, Lin CJ (2008) Liblinear: a library for large linear classification. J Mach Learn Res 9(9):1871–1874
Feng X, Ling Z, Lunwen W (2004) The approach of the fuzzy granular computing based on the theory of quotient space. Pattern Recognit Artif Intell 17(4):124–129
Fu G, Hou C, Yao X (2019) Learning topological representation for networks via hierarchical sampling. arXiv:190206684
Grover A, Leskovec J (2016) node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, ACM, pp 855–864
Hobbs JR (1990) Granularity. In: Readings in qualitative reasoning about physical systems, Elsevier, Amsterdam, pp 542–545
Jie T, Jing Z, Yao L, Li J, Zhong S (2008) Arnetminer: extraction and mining of academic social networks. In: ACM Sigkdd international conference on knowledge discovery and data mining
LIANG J, QIAN Y, LI D, HU Q (2015) Theory and method of granular computing for big data mining. Sci Sin Inf 45(11):1355
Liang J, Gurukar S, Parthasarathy S (2018) Mile: a multi-level framework for scalable graph embedding. arXiv:180209612
Liben-Nowell D, Kleinberg J (2007) The link-prediction problem for social networks. J Am Soc Inf Sci Technol 58(7):1019–1031
Lin T (1997) Granular computing: From rough sets and neighborhood systems to information granulation and computing in words. In: European congress on intelligent techniques and soft computing, pp 1602–1606
Lin TY (1999) Granular computing: fuzzy logic and rough sets. In: Computing with words in information/intelligent systems 1, Springer, New York, pp 183–200
Lin TY (2003) Granular computing. In: International workshop on rough sets, fuzzy sets, data mining, and granular-soft computing, Springer, New York, pp 16–24
Mao J, Zheng T, Zhang L (2004) Biological sequence alignments based on quotient space. Comput Eng Appl 34(14):15–17
Ou M, Cui P, Pei J, Zhang Z, Zhu W (2016) Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp 1105–1114
Palla G, Derényi I, Farkas I, Vicsek T (2005) Uncovering the overlapping community structure of complex networks in nature and society. Nature 435(7043):814
Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11(5):341–356
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, pp 701–710
Perozzi B, Kulkarni V, Chen H, Skiena S (2017) Don’t walk, skip!: Online learning of multi-scale network embeddings. In: Proceedings of the 2017 IEEE/ACM international conference on advances in social networks analysis and mining 2017, ACM, pp 258–265
Qi J, Wei L, Wan Q (2019) Multi-level granularity in formal concept analysis. Granular Comput 4(3):351–362
Qian J, Liu C, Yue X (2019) Multigranulation sequential three-way decisions based on multiple thresholds. Int J Approx Reason 105:396–416
Qian Y, Liang J, Yao Y, Dang C (2010) Mgrs: a multi-granulation rough set. Inf Sci 180(6):949–970
Rauber PE, Falcão AX, Telea AC (2016) Visualizing time-dependent data using dynamic t-sne. In: Proceedings of the Eurographics/IEEE VGTC conference on visualization: short papers, Eurographics association, pp 73–77
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, International World Wide Web Conferences Steering Committee, pp 1067–1077
Theocharidis A, Van Dongen S, Enright AJ, Freeman TC (2009) Network visualization and analysis of gene expression data using biolayout express 3d. Nat Protocols 4(10):1535–1550
Tu C, Yang C, Liu Z, Sun S (2017) Network representation learning: an overview (in chinese). Sci Sin Inf 47:980–996
Wang G (2017) Data-driven granular cognitive computing. In: international joint conference on rough sets, Springer, New York, pp 13–24
Wang G, Yang J, Xu J (2017) Granular computing: from granularity optimization to multi-granularity joint problem solving. Granular Comput 2(3):105–120
Wang X, Cui P, Wang J, Pei J, Zhu W, Yang S (2017) Community preserving network embedding. In: 31st AAAI conference on artificial intelligence
Xu F, Zhang L (2005) An analysis of uneven granules clustering based on quotient space. Comput Eng 31(3):26–28
Yao Y (2001) Information granulation and rough set approximation. Int J Intell Syst 16(1):87–104
Yao Y (2016) A triarchic theory of granular computing. Granular Comput 1(2):145–157
Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353
Zadeh LA (1997) Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst 90(2):111–127
Zhang B, Zhang L (1992) Theory and applications of problem solving, vol 9. North-Holland, Amsterdam
Zhang L, Zhang B (1990) Theory and applications of problem solving. 1st version
Zhang L, Zhang B (2007) The theory of quotient space and its applications. 2nd version
Zhang L, Fg H, Yp Z, Zhao S (2009) A new algorithm for optimal path finding in complex networks based on the quotient space. Fund Inf 93(4):459–469
Zhang M, Wu T, Wang L, Cheng J (2003) The application of granularity of the quotient space theory in database and data warehouse. J Comput Eng Appl 39(17):47–49
Zhang Y, Cui G, Deng S, He Q (2016) Alliance-aware service composition based on quotient space. In: 2016 IEEE international conference on web services (ICWS), IEEE, pp 340–347
Zhao L, Yao Y, Ling Z (2017) Measurement of general granules. Inf Sci 415–416:128–141
Zhao S, Sun X, Chen J, Duan Z, Zhang Y, Zhang Y (2018) Relational granulation method based on quotient space theory for maximum flow problem. Inf Sci
Acknowledgements
This work was partially supported by the National Natural Science Foundation of China (Grants #61876001, #61602003, #61673020), National High Technology Research and Development Program (Grant #2017YFB1401903), the Provincial Natural Science Foundation of Anhui Province (Grant #1708085QF156), and the Recruitment Project of Anhui University for Academic and Technology Leader.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Chen, J., Du, Z., Sun, X. et al. A multi-granular network representation learning method. Granul. Comput. 6, 59–68 (2021). https://doi.org/10.1007/s41066-019-00194-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41066-019-00194-2