Abstract
Role embedding aims to embed role-similar nodes into similar representations. Role embedding is significant in graph mining, providing a key bridge between traditional role analysis and machine learning. However, current methods suffer from information loss due to the inherent drawbacks, thus failing to capture role information comprehensively from both global and local perspectives. This paper proposes RED (Role Embedding via Discrete-time quantum walk) to address the above issue via quantum walks, whose characters are naturally applicable to role embedding. Based on the superposition, RED simultaneously learns global role representations by evolving features in a global evolution. Besides, RED uses the quasi-periodicity to capture long-term evolving features within steps. To represent local role information, RED simulates a wave-like diffusion by biased walks, where it learns the closeness from accumulated probabilities for local role representations. To the best of our knowledge, RED is the first to apply quantum walks to the role embedding. Substantial experiments demonstrate that RED significantly outperforms state-of-the-art methods by up to 2300.00% in role detection, 90.93% in equivalency identification, and is overwhelmingly superior in robustness.
Similar content being viewed by others
Notes
Node2vec is available on https://github.com/aditya-grover/node2vec, Rolx is available on https://github.com/dkaslovsky/GraphRole, Role2vec is available on https://github.com/benedekrozemberczki/role2vec, and GraphWave is available on https://github.com/benedekrozemberczki/GraphWaveMachine.
References
Rossi RA, Ahmed NK (2014) Role discovery in networks. IEEE Trans Knowl Data Eng 27 (4):1112–1131
Jin R, Lee VE, Hong H (2011) Axiomatic ranking of network role similarity. In: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 922–930
Donnat C, Zitnik M, Hallac D, Leskovec J (2018) Learning structural node embeddings via diffusion wavelets. In: International ACM conference on knowledge discovery and data mining (KDD), pp 1320–1329. ACM
FR Ribeiro L, HP Saverese P, R Figueiredo D (2017) struc2vec: Learning node representations from structural identity. In: International ACM conference on knowledge discovery and data mining (KDD), pp 385–394. ACM
Ahmed NK, Rossi RA, Lee JB, Kong X, Willke TL, Zhou R, Eldardiry H (2018) Learning role-based graph embeddings. stat 1050:7
Grover A, Leskovec J (2016) node2vec: Scalable feature learning for networks. In: International ACM conference on knowledge discovery and data mining (KDD), pp 855–864. ACM
Henderson K, Gallagher B, Eliassi-Rad T, Tong H, Basu S, Akoglu L, Koutra D, Faloutsos C, Lei L (2012) Rolx:structural role extraction & mining in large graphs. In: International ACM conference on knowledge discovery and data mining (KDD), pp 1231–1239. ACM
Childs AM (2010) On the relationship between continuous-and discrete-time quantum walk. Commun Math Phys 294(2):581–603
Rohde PP, Fedrizzi A, Ralph TC (2012) Entanglement dynamics and quasi-periodicity in discrete quantum walks. J Mod Opt 59(8):710–720
Perozzi B, Alrfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: International ACM conference on knowledge discovery and data mining (KDD), pp 701–710. ACM
Ma X, Qin G, Qiu Z, Zheng M, Wang Z (2019) Riwalk: Fast structural node embedding via role identification. In: IEEE ICDM 2019
Henderson K, Gallagher B, Li L, Akoglu L, Eliassi-Rad T, Tong H, Faloutsos C (2011) It’s who you know: Graph mining using recursive structural features. In: International ACM conference on knowledge discovery and data mining (KDD), pp 663–671. ACM
A DKH, B PV, c RG (2011) Wavelets on graphs via spectral graph theory. Appl Comput Harmon Anal 30(2):129–150
Tu K, Cui P, Wang X, Yu PS, Zhu W (2018) Deep recursive network embedding with regular equivalence. In: the 24th ACM SIGKDD International Conference
Ba JL, Kiros JR, Hinton GE (2016) Layer normalization
Portugal R (2013) Quantum walks and search algorithms. Springer, New York
Farhi E, Gutmann S (1998) Quantum computation and decision trees. Phys Rev A 58 (2):915–928
Feynman RP, Hibbs AR, Weiss GH (1965) Quantum mechanics and path integrals. McGraw-Hill, New York
Grover LK (1996) A fast quantum mechanical algorithm for database search. In: Acm symposium on theory of computing, pp 212–219
Venegas-Andraca SE (2012) Quantum walks: a comprehensive review. Quantum Inf Process
Douglas B, Wang J (2008) A classical approach to the graph isomorphism problem using quantum walks. J Phys A 41(7):075303
Junjie W, Baida Z, Yuhua T, Xiaogang Q, Huiquan W (2013) Finding tree symmetries using continuous-time quantum walk. Chinese Physics B 22(5):050304
Izaac JA, Zhan X, Bian Z, Wang K, Li J, Wang JB, Xue P (2017) Centrality measure based on continuous-time quantum walks and experimental realization. Phys Rev A 95(3):032318
Loke T, Tang JW, Rodriguez JPJ, Small M, Wang J (2017) Comparing classical and quantum pageranks. Quantum Inf Process 16(1):1–22
Mahasinghe A, Wang JB, Wijerathna JK (2014) Quantum walk-based search and symmetries in graphs. J Phys A Math Theor 47(50):505301
Wang X, Lu K, Zhang Y, Liu K (2020) Qsim: A novel approach to node proximity estimation based on discrete-time quantum walk. Appl Intell. https://doi.org/10.1007/s10489-020-01970-3
Emms D, Wilson RC, Hancock ER (2009) Graph matching using the interference of discrete-time quantum walks. Image Vis Comput 27(7):934–949
Cross R, Parker A, Christensen CM, Anthony SD, Roth EA (2004) The hidden power of social networks. J App Management & Entrepreneurship 9(Oct)
De Nooy W, Mrvar A, Batagelj V (2018) Exploratory social network analysis with pajek: Revised and expanded edition for updated software, vol 46. Cambridge University Press, Cambridge
Kunegis J (2013) Konect: the koblenz network collection. In: Proceedings of the 22nd international conference on world wide web, pp 1343–1350. ACM
Newman Mark EJ (2006) Modularity and community structure in networks. Proc Natl Acad Sci U S A 103(23):8577–8582
Girvan M, Newman Mark EJ (2002) Community structure in social and biological networks. Proc Natl Acad Sci U S A 99(12):7821–7826
Guimera R, Danon L, Diaz-Guilera A, Giralt F, Arenas A (2003) Self-similar community structure in a network of human interactions. Physical review E 68(6):065103
Adamic LA, Glance N (2005) The political blogosphere and the 2004 us election: divided they blog. In: Proceedings of the 3rd international workshop on link discovery, pp 36–43. ACM
Moody J (2001) Peer influence groups: identifying dense clusters in large networks. Soc Networks 23(4):261–283
Leskovec J, Kleinberg J, Faloutsos C (2007) Graph evolution: Densification and shrinking diameters. ACM Transactions on Knowledge Discovery from Data (TKDD) 1(1):2
Tang L, Liu H (2009) Relational learning via latent social dimensions. In: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp 817–826
Vinh NX, Epps J, Bailey J (2010) Information theoretic measures for clusterings comparison: Variants, properties, normalization and correction for chance. J Mach Learn Res 11:2837–2854
Rand WM (1971) Objective criteria for the evaluation of clustering methods. Publ Am Stat Assoc 66(336):846–850
Rosenberg A, Hirschberg J (2007) V-measure: A conditional entropy-based external cluster evaluation measure. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL), pp 410–420
Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20(1):53–65
Acknowledgements
This work is supported by National High-level Personnel for Defense Technology Program (2017-JCJQ-ZQ-013), NSF 61902405, NSF 62002371, and the China Scholarship Council (CSC Student ID 201903170136). This work is partially done during my research visit to School of Computing, National University of Singapore, under the supervision of Prof. Xiaokui XIAO.
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.
Xin Wang and Sonelei Jian are contributed equally to this work.
Rights and permissions
About this article
Cite this article
Wang, X., Jian, S., Lu, K. et al. RED: Learning the role embedding in networks via Discrete-time quantum walk. Appl Intell 52, 1493–1507 (2022). https://doi.org/10.1007/s10489-021-02342-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02342-1