Abstract
The task of link prediction has become a fundamental research problem in the analysis of complex networks. However, most existing non-negative matrix factorization (NMF) methods are decoding models and solely consider a single type of structural information around node pairs in networks, resulting in sub-optimal prediction accuracy. To solve these limitations, we propose a novel model, namely Graph Regularized Autoencoder-inspired Non-negative Matrix Factorization via jointly Clustering information and Biased random walk (GRANMFCB for short), for link prediction. Specifically, GRANMFCB comprises both encoder and decoder components, fully leveraging the advantages of autoencoders. In addition, clustering information and high-order structures are utilized to preserve abundant structural information around node pairs and against sparsity of networks. Finally, effective iterative multi-multiplication updating rules are proposed to optimize the objective function and the convergence is strictly proved. Extensive experimental results on twelve real-world networks show that our proposed model outperforms the state-of-the-art approaches. Codes are available at https://github.com/litongf/GRANMFCB.
Similar content being viewed by others
References
Kumar A, Singh SS, Singh K et al (2020) Link prediction techniques, applications, and performance: a survey. Physica A: Stat Mech Appl 553:124289
Wang W, Feng Y, Jiao P et al (2017) Kernel framework based on non-negative matrix factorization for networks reconstruction and link prediction. Knowl-Based Syst 137(Dec 1):104–114
Yao Y, Zhang R, Yang F et al (2018) Link prediction in complex networks based on the interactions among paths. Physica A: Stat Mech Appl 510:52–67
Yao Y, Cheng T, Li X et al (2023) Link prediction based on the mutual information with high-order clustering structure of nodes in complex networks. Physica A: Stat Mech Appl 610:128428
Akbar JA, Anthony K, Wu FX (2020) MDIPA: a microRNA-drug interaction prediction approach based on non-negative matrix factorization. Bioinformatics 36(20):5061–5067
Lv L, Zhou T (2011) Link prediction in complex networks: a survey. Physica A: Stat Mech Appl 390:1150–1170
Gu Q, Zhou J, Chris H. Q. Ding (2010) Collaborative filtering: weighted nonnegative matrix factorization incorporating user and item graphs. In: SIAM International Conference on Data Mining, pp 199–210
Zhao Z, Gou Z, Du Y et al (2022) A novel link prediction algorithm based on inductive matrix completion. Expert Syst Appl 188:116033
Xia F, Sun K, Yu S et al (2021) Graph learning: a survey. IEEE Trans Artif Intell 2(2):109–127
Tang M, Yu W, Li X et al (2022) Cold-start link prediction via weighted symmetric nonnegative matrix factorization with graph regularization. Comp Syst Sci Eng 43(3):1069–1084
Menon AK, Elkan C (2011) Link prediction via matrix factorization. In: Machine learning and knowledge discovery in databases - European Conference, ECML PKDD 2011, Athens, Greece, September 5–9, 2011, Proceedings, Part II
Chen B, Li F, Chen S et al (2017) Link prediction based on non-negative matrix factorization. PLoS ONE 12(8):e0182968
Ma X, Sun P, Qin G (2017) Nonnegative matrix factorization algorithms for link prediction in temporal networks using graph communicability. Patt Recognit 71:361–374
Chen G, Xu C, Wang J et al (2020) Nonnegative matrix factorization for link prediction in directed complex networks using pagerank and asymmetric link clustering information. Expert Syst Appl 148:113290
Chen G, Xu C, Wang J et al (2019) Graph regularization weighted nonnegative matrix factorization for link prediction in weighted complex network. Neurocomputing 369(Dec 5):50–60
Mahmoodi R, Seyedi SA, Akhlaghian Tab F et al (2023) Link prediction by adversarial nonnegative matrix factorization. Knowl-Based Syst 280:110998
MartAnez V, Berzal F, Cubero JC (2016) A survey of link prediction in complex networks. ACM Comput Surv 49(4):1–33
Lorrain F, White HC (1971) The structural equivalence of individuals in social networks. J Math Sociol 1(1):49–80
Adamic LA, Adar E (2003) Friends and neighbors on the web. Social Netw 25(3):211–230
Zhou T, Lü L, Zhang YC (2009) Predicting missing links via local information. Eur Phys J B 71(4):623–630
Katz L (1953) A new status index derived from sociometric analysis. Psychometrika 18(1):39–43
Salton G (1983) Introduction to modern information retrieval. Inform Process Manag 19:402–403
Ahmad I, Akhtar MU, Noor S et al (2020) Missing link prediction using common neighbor and centrality based parameterized algorithm. Scient Report 10(1):364
Rafiee S, Salavati C, Abdollahpouri A (2020) Cndp: link prediction based on common neighbors degree penalization. Physica A: Stat Mech Appl 539:122950
Liu W, Lv L (2010) Link prediction based on local random walk. Europhys Lett 89(5):58007
Aziz F, Gul H, Muhammad I et al (2020) Link prediction using node information on local paths. Physica A: Stat Mech Appl 557:124980
Leicht EA, Holme P, Newman MEJ (2006) Vertex similarity in networks. Phys Rev E Stat Nonlin Soft Matt Phys 73(2 Pt 2):026120
Brin S (2012) The anatomy of a large-scale hypertextual Web search engine. Comp Netw ISDN Syst 30(1):107–177
Wang C, Satuluri V, Parthasarathy S (2007) Local probabilistic models for link prediction. In: Seventh IEEE International Conference on Data Mining (ICDM 2007) pp. 322–331
Clauset A, Moore C, Newman ME (2008) Hierarchical structure and the prediction of missing links in networks. Nature 453:98–101
Guimera R, Sales-Pardo M et al (2009) Missing and spurious interactions and the reconstruction of complex networks. Proceed Nat Acad Sci 106(52):22073–22078
Kuang J, Scoglio C (2021) Layer reconstruction and missing link prediction of a multilayer network with maximum \(a \mathit{posteriori}\) estimation. Phys Rev E 104:024301
Pech R, Hao D et al (2017) Link prediction via matrix completion. EPL (Europhys Lett) 117(3):38002
Wang Z, Liang J, Li R (2018) A fusion probability matrix factorization framework for link prediction. Knowl-Based Syst 159:72–85
Zhuangwei Shi CJXQYYHan Zhang (2021) A representation learning model based on variational inference and graph autoencoder for predicting lncrna-disease associations. BMC Bioinform 22(1):136
Yulian Ding BLFXWXiujuan Lei (2022) Predicting mirna-disease associations based on multi-view variational graph auto-encoder with matrix factorization. IEEE J Biomed Health Inform 26(1):446–457
Chen Jin KLHZZhuangwei Shi (2022) Predicting mirna-disease association based on neural inductive matrix completion with graph autoencoders and self-attention mechanism. Biomolecules 12(1):64
Gao H, Sun J et al (2023) Predicting metabolite-disease associations based on auto-encoder and non-negative matrix factorization. Brief Bioinform 24(5):1259
Zhang M, Chen Y (2017) Weisfeiler-lehman neural machine for link prediction. In: the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 575–583
Li JC, Zhao DL, Ge BF et al (2017) A link prediction method for heterogeneous networks based on bp neural network. Physica A: Stat Mech Appl 495:1–17
Zhou M, Jin H, Wu Q et al (2022) Betweenness centrality-based community adaptive network representation for link prediction. Appl Intell 52(4):3545–3558
Esa B, Mr A, Ma B (2015) Structural link prediction based on ant colony approach in social networks. Physica A: Stat Mech Appl 419:80–94
Chen J, Wu Y, Xu X et al (2019) Pso-ane: adaptive network embedding with particle swarm optimization. IEEE Trans Comput Social Syst 6(4):649–659
Cao Z, Zhang Y et al (2019) A chaotic ant colony optimized link prediction algorithm. IEEE Trans Syst, Man, Cybern: Syst 99:1–15
Arrar D, Kamel N, Lakhfif A (2023) A comprehensive survey of link prediction methods. J Supercomp 80(3):3902–3942
Zhou T (2023) Discriminating abilities of threshold-free evaluation metrics in link prediction. Physica A: Stat Mech Appl 615:128529
Hanley J (1982) The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology 143(1):29–36
Lee DD, Seung HS (2000) Algorithms for non-negative matrix factorization. In: International Conference on Neural Information Processing Systems, p 535-541
Lee DD, Seung HS (1999) Learning the parts of objects by nonnegative matrix factorization. Nature 401(6755):788–791
Qian Y, Dong E, Zheng X (2014) Link prediction via nonnegative matrix factorization enhanced by blocks information. In: 2014 10th International Conference on Natural Computation (ICNC) IEEE, pp. 823–827
He X, Huang TS, Cai D et al (2011) Graph regularized nonnegative matrix factorization for data representation. IEEE Trans Patt Anal Mach Intell 33(08):1548–1560
Sun BJ, Shen H, Gao J, et al (2017) A non-negative symmetric encoder-decoder approach for community detection. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, p. 597–606
Wu Z, Lin Y, Wan H et al (2016) Predicting top-l missing links with node and link clustering information in large-scale networks. J Stat Mech: Theory Exper 8:083202
Cheng Y, Sun M, Liu Z et al (2017) Fast network embedding enhancement via high order proximity approximation. Int Jt Conf Artif Intell 894:3900
Yang C, Liu Z, Zhao D et al (2015) Network representation learning with rich text information. IJCAI 2015:2111–2117
Boyd S, Vandenberghe L (2004) Convex optimization. Cambridge University Press, Cambridge
Ding C, Li T, Jordan MI (2010) Convex and semi-nonnegative matrix factorizations. IEEE Trans Patt Anal Mach Intell 32(1):45–55
Kunegis J (2013) KONECT – The Koblenz Network Collection, pp 1343–1350
Guo G, Zhang J, Yorke-Smith N (2013) A novel evidence-based Bayesian similarity measure for recommender systems
Newman M (2001) Clustering and preferential attachment in growing networks. Phys Rev E Stat Nonlin Soft Matter Phys 64:025102
Pech R, Hao D, Lee YL et al (2019) Link prediction via linear optimization. Physica A: Stat Mech Appl 528:121319
Liu XC, Meng DQ, Zhu XZ et al (2020) Link prediction based on contribution of neighbors. Int J Modn Phys C 31(11):2050158
Wu Z, Lin Y, Wang J et al (2016) Link prediction with node clustering coefficient. Physica A: Stat Mech Appl 452:1–8
Zhou T, Lee YL, Wang G (2021) Experimental analyses on 2-hop-based and 3-hop-based link prediction algorithms. Physica A: Stat Mech Appl 564:125532
Liu Z, Zhang QM, Lu L et al (2011) Link prediction in complex networks: a local Naive Bayes model. EPL (Europhys Lett) 96:48007
Tian Y, Nie G, Tian H et al (2023) Impact of endpoint structure attributes on local information algorithms based on link prediction. Computing 105(1):115–129
Chen G, Wang H, Fang Y et al (2022) Link prediction by deep non-negative matrix factorization. Expert Syst Appl 188:115991
Cai J, Hu J, Tang X et al (2020) Deep historical long short-term memory network for action recognition. Neurocomputing 407:428–438
Acknowledgements
This work is supported by Qinghai Normal University young and middle-aged research fund project(2023QZR011), Qinghai Key Laboratory of Internet of Things, Focus on research and development and achievement transformation project in Qinghai province (Grant No: 2022-GX-155), the National Natural Science Foundation of China (No. 62366030), the Gansu Provincial Natural Science Foundation (No. 23JRRA8222), the Higher Education Innovation Fund project of Gansu (No. 2022A-022), the Open Project of Key Laboratory of Linguistic and Cultural Computing Ministry of Education (No. KFKT202304).
Author information
Authors and Affiliations
Contributions
TL and RZ Conceptualization, Methodology, Software, Writing—original draft, Visualization, Investigation, Validation, Writing—review & editing, Supervision. YY, YL, JM and JT: Writing—review & editing, Data curation. All authors reviewed the manuscript.
Corresponding authors
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A: Parameters of compared baselines
Appendix A: Parameters of compared baselines
The rest of parameters of compared baselines are set as their suggestion values. For LO, the \(\alpha\) is set to 0.0001 and the \(\beta _{1}\) of CNDP is set to 1.8. The parameters of NC and LPANMF are respectively set to 0.85 and 2.2. Besides, the layer configure information of FSSDNMF is set as [64 32 16] on the networks Convote, Filmtrust, Adolescent health, Powergrid, Physicians, Bcspr09, Football, Pdzbase, Dvdtrust, Chess and Gnutella. For network Karate, the layer configure information of FSSDNMF is set as [16 8 4].
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Li, T., zhang, R., Yao, Y. et al. Graph regularized autoencoding-inspired non-negative matrix factorization for link prediction in complex networks using clustering information and biased random walk. J Supercomput (2024). https://doi.org/10.1007/s11227-024-06013-z
Accepted:
Published:
DOI: https://doi.org/10.1007/s11227-024-06013-z