{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T16:06:11Z","timestamp":1779120371529,"version":"3.51.4"},"reference-count":71,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Link prediction is a crucial task in complex network analysis, aiming to predict future connections between nodes in a graph. This problem is particularly challenging in sparse networks, where the low number of edges complicates traditional prediction methods. To address this, we propose singular value decomposition-graph attention network-gradient boosting (SVD-GAT-GB), a hybrid approach that densifies the sparse graph using truncated SVD, improves node representations through a GAT, and applies GB for accurate link prediction. Our method effectively handles the sparsity issue, significantly enhancing the prediction accuracy by leveraging structural information extracted from the densified graph. We validate our approach through extensive experiments on multiple datasets, demonstrating improvements in both F1-score and AUC by approximately 32% and 11%, respectively, over existing methods. The proposed model proves to be accurate and robust across diverse types of networks, making it an effective solution for link prediction in sparse graphs.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf144","type":"journal-article","created":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T12:47:02Z","timestamp":1766234822000},"page":"773-785","source":"Crossref","is-referenced-by-count":0,"title":["Singular value decomposition-based graph densification for link prediction in sparse graphs"],"prefix":"10.1093","volume":"69","author":[{"given":"Amir","family":"Hossein Pouria","sequence":"first","affiliation":[{"name":"Department of Computer Engineering , Amirkabir University of Technology (Tehran Polytechnic), No. 350, Hafez Ave, Valiasr Square, Tehran,","place":["Iran"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mostafa","family":"Haghir Chehreghani","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering , Amirkabir University of Technology (Tehran Polytechnic), No. 350, Hafez Ave, Valiasr Square, Tehran,","place":["Iran"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alireza","family":"Bagheri","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering , Amirkabir University of Technology (Tehran Polytechnic), No. 350, Hafez Ave, Valiasr Square, Tehran,","place":["Iran"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"2026051811065224800_ref1","doi-asserted-by":"crossref","first-page":"128428","DOI":"10.1016\/j.physa.2022.128428","article-title":"Link prediction based on the mutual information with high-order clustering structure of nodes in complex networks","volume":"610","author":"Yao","year":"2023","journal-title":"Phys Stat Mech Appl"},{"key":"2026051811065224800_ref2","article-title":"Link prediction in social networks: the state-of-the-art","volume":"58","author":"Wang","year":"2014","journal-title":"Sci China Inform Sci"},{"key":"2026051811065224800_ref3","first-page":"151","article-title":"Improve the accuracy of link predictions on sparse networks based on similarity measures and multiple ensemble learning","volume":"11","author":"Kim","year":"2020","journal-title":"J Inf Hiding Multim Signal Process"},{"key":"2026051811065224800_ref4","doi-asserted-by":"crossref","DOI":"10.1007\/s13042-018-0823-8","article-title":"On relational learning and discovery in social networks: a survey","volume":"10","author":"Zhang","year":"2019","journal-title":"Int J Mach Learn Cybern"},{"key":"2026051811065224800_ref5","doi-asserted-by":"crossref","DOI":"10.1145\/3341161.3342890","article-title":"GEMSEC: graph embedding with self clustering","volume-title":"Proceedings of the 2019 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining, New York, NY, USA, August ASONAM \u201819 65\u201372","author":"Rozemberczki","year":"2019"},{"key":"2026051811065224800_ref6","article-title":"Representation learning on graphs: methods and applications","volume-title":"IEEE Data Engineering Bulletin","author":"Hamilton","year":"2018"},{"key":"2026051811065224800_ref7","doi-asserted-by":"publisher","first-page":"5834","DOI":"10.1109\/TNNLS.2018.2812888","article-title":"Learning to map social network users by unified manifold alignment on hypergraph","volume":"29","author":"Zhao","year":"2018","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"2026051811065224800_ref8","doi-asserted-by":"crossref","first-page":"118737","DOI":"10.1016\/j.eswa.2022.118737","article-title":"Link prediction approach combined graph neural network with capsule network","volume":"212","author":"Liu","year":"2023","journal-title":"Expert Syst Appl"},{"key":"2026051811065224800_ref9","doi-asserted-by":"crossref","first-page":"124289","DOI":"10.1016\/j.physa.2020.124289","article-title":"Link prediction techniques, applications, and performance: a survey","volume":"553","author":"Kumar","year":"2020","journal-title":"Phys Stat Mech Appl"},{"key":"2026051811065224800_ref10","doi-asserted-by":"crossref","first-page":"5274","DOI":"10.1109\/TSMC.2019.2947516","article-title":"A chaotic ant colony optimized link prediction algorithm","volume":"51","author":"Cao","year":"2021","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"2026051811065224800_ref11","article-title":"DSN-DDI: an accurate and generalized framework for drug\u2013drug interaction prediction by dual-view representation learning","volume":"24","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026051811065224800_ref12","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1145\/3038912.3052569","article-title":"Neural collaborative filtering","volume-title":"Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, April","author":"He","year":"2017"},{"key":"2026051811065224800_ref13","doi-asserted-by":"crossref","first-page":"112839","DOI":"10.1016\/j.eswa.2019.112839","article-title":"Friend recommendation for cross marketing in online brand community based on intelligent attention allocation link prediction algorithm","volume":"139","author":"Li","year":"2019","journal-title":"Expert Syst Appl"},{"key":"2026051811065224800_ref14","doi-asserted-by":"crossref","first-page":"125154","DOI":"10.1016\/j.physa.2020.125154","article-title":"Link prediction in recommender systems based on vector similarity","volume":"560","author":"Su","year":"2020","journal-title":"Phys Stat Mech Appl"},{"key":"2026051811065224800_ref15","article-title":"An ecommerce recommendation algorithm based on link prediction","volume":"61","author":"Liu","year":"2021","journal-title":"Alex Eng J"},{"key":"2026051811065224800_ref16","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.neucom.2016.06.024","article-title":"Presenting new collaborative link prediction methods for activity recommendation in facebook","volume":"210","author":"Shahmohammadi","year":"2016","journal-title":"Neurocomputing"},{"key":"2026051811065224800_ref17","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-09177-y","article-title":"Network-based prediction of protein interactions","volume":"10","author":"Kov\u00e1cs","year":"2019","journal-title":"Nat Commun"},{"key":"2026051811065224800_ref18","doi-asserted-by":"crossref","first-page":"025103","DOI":"10.1103\/PhysRevE.69.025103","article-title":"Structural vulnerability of the North American power grid","volume":"69","author":"Albert","year":"2004","journal-title":"Phys Rev E"},{"key":"2026051811065224800_ref19","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1038\/srep01344","article-title":"Emergence of network features from multiplexity","volume":"3","author":"Cardillo","year":"2013","journal-title":"Sci Rep"},{"key":"2026051811065224800_ref20","article-title":"Personalized recommendation by matrix co-factorization with tags and time information","volume":"119","author":"Luo","year":"2018","journal-title":"Expert Syst Appl"},{"key":"2026051811065224800_ref21","doi-asserted-by":"crossref","first-page":"38938","DOI":"10.1038\/srep38938","article-title":"A perturbation-based framework for link prediction via non-negative matrix factorization","volume":"6","author":"Wang","year":"2016","journal-title":"Sci Rep"},{"key":"2026051811065224800_ref22","doi-asserted-by":"crossref","first-page":"116033","DOI":"10.1016\/j.eswa.2021.116033","article-title":"A novel link prediction algorithm based on inductive matrix completion","volume":"188","author":"Zhao","year":"2021","journal-title":"Expert Syst Appl"},{"key":"2026051811065224800_ref23","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.neucom.2019.01.028","article-title":"A deep variational matrix factorization method for recommendation on large scale sparse dataset","volume":"334","author":"Zhang","year":"2019","journal-title":"Neurocomputing"},{"key":"2026051811065224800_ref24","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/1117454.1117460","article-title":"The case for anomalous link discovery","volume":"7","author":"Rattigan","year":"2005","journal-title":"SIGKDD Explor"},{"key":"2026051811065224800_ref25","article-title":"You only transfer what you share: intersection-induced graph transfer learning for link prediction.","volume-title":"Transactions on Machine Learning Research","author":"Zheng","year":"2023"},{"key":"2026051811065224800_ref26","first-page":"1","article-title":"Deep non-negative matrix factorization with edge generator for link prediction in complex networks","volume":"54","author":"Yao","year":"2023","journal-title":"Appl Intell"},{"key":"2026051811065224800_ref27","doi-asserted-by":"crossref","first-page":"115991","DOI":"10.1016\/j.eswa.2021.115991","article-title":"Link prediction by deep non-negative matrix factorization","volume":"188","author":"Chen","year":"2022","journal-title":"Expert Syst Appl"},{"key":"2026051811065224800_ref28","first-page":"1","article-title":"Link prediction using deep autoencoder-like non-negative matrix factorization with l21-norm","volume":"54","author":"Li","year":"2024","journal-title":"Appl Intell"},{"key":"2026051811065224800_ref29","first-page":"477","article-title":"Link prediction in sparse networks by incidence matrix factorization","volume":"25","author":"Yokoi","year":"2017","journal-title":"J Inf Process"},{"key":"2026051811065224800_ref30","first-page":"183","article-title":"Overcoming the link prediction limitation in sparse networks using community detection","volume":"9","author":"Salvati","year":"2021","journal-title":"J Inf Syst Telecommun"},{"key":"2026051811065224800_ref31","doi-asserted-by":"crossref","first-page":"57874","DOI":"10.1109\/ACCESS.2021.3073249","article-title":"SSNE: effective node representation for link prediction in sparse networks","volume":"9","author":"Chen","year":"2021","journal-title":"IEEE Access"},{"key":"2026051811065224800_ref32","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1093\/comjnl\/bxy040","article-title":"Discriminative distance-based network indices with application to link prediction","volume":"61","author":"Chehreghani","year":"2018","journal-title":"Comput J"},{"key":"2026051811065224800_ref33","doi-asserted-by":"crossref","first-page":"025102","DOI":"10.1103\/PhysRevE.64.025102","article-title":"Clustering and preferential attachment in growing networks","volume":"64","author":"Newman","year":"2001","journal-title":"Phys Rev E"},{"key":"2026051811065224800_ref34","volume-title":"Introduction to Modern Information Retrieval","author":"Salton","year":"1983"},{"key":"2026051811065224800_ref35","first-page":"241","article-title":"Distribution de la flore alpine dans le bassin des dranses et dans quelques r\u00e9gions voisines","volume":"37","author":"Jaccard","year":"1901","journal-title":"Bull Soc Vaud Sci Nat"},{"key":"2026051811065224800_ref36","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0378-8733(03)00009-1","article-title":"Friends and neighbors on the web","volume":"25","author":"Adamic","year":"2003","journal-title":"Social Networks"},{"key":"2026051811065224800_ref37","doi-asserted-by":"crossref","first-page":"021102","DOI":"10.1103\/PhysRevE.75.021102","article-title":"Power-law strength-degree correlation from a resource-allocation dynamics on weighted networks","volume":"75","author":"Ou","year":"2007","journal-title":"Phys Rev E Stat Nonlin Soft Matter Phys"},{"key":"2026051811065224800_ref38","doi-asserted-by":"crossref","DOI":"10.1016\/j.physa.2019.121397","article-title":"Link prediction based on linear dynamical response","volume":"527","author":"Gao","year":"2019","journal-title":"Phys Stat Mech Appl"},{"key":"2026051811065224800_ref39","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/S1005-8885(11)60425-1","article-title":"Probabilistic latent tensor factorization model for link pattern prediction in multi-relational networks","volume":"19","author":"Gao","year":"2012","journal-title":"J China Univ Posts Telecommun"},{"key":"2026051811065224800_ref40","article-title":"A Bayesian tensor factorization model via variational inference for link prediction. arXiv preprint arXiv","author":"Ermis","year":"2014; 1409.8276"},{"key":"2026051811065224800_ref41","first-page":"823","article-title":"Link prediction via nonnegative matrix factorization enhanced by blocks information","volume-title":"2014 10th International Conference on Natural Computation (ICNC), Xiamen, China, August","author":"Yang","year":"2014"},{"key":"2026051811065224800_ref42","article-title":"Creatinine clearance estimations for vancomycin maintenance dose adjustments","volume":"25","author":"\u0160\u00edma","year":"2017","journal-title":"Am J Ther"},{"key":"2026051811065224800_ref43","first-page":"1039","article-title":"Statistical link label modeling for sign prediction: Smoothing sparsity by joining local and global information","volume-title":"2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA, November.","author":"Javari","year":"2017"},{"key":"2026051811065224800_ref44","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24\u201326, 2017, Conference Track Proceedings, Toulon, France, April 0","author":"Kipf"},{"key":"2026051811065224800_ref45","article-title":"Graph attention networks","volume-title":"International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, April 30 - May 3 0","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2026051811065224800_ref46","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1038\/s42256-022-00466-8","article-title":"Half a decade of graph convolutional networks","volume":"4","author":"Chehreghani","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2026051811065224800_ref47","doi-asserted-by":"crossref","first-page":"24638","DOI":"10.1007\/s11227-024-06336-x","article-title":"Centrality-based and similarity-based neighborhood extension in graph neural networks","volume":"80","author":"Zohrabi","year":"2024","journal-title":"J Supercomput"},{"key":"2026051811065224800_ref48","article-title":"Learning from counterfactual links for link prediction.","author":"Zhao"},{"key":"2026051811065224800_ref49","article-title":"Deepened graph auto-encoders help stabilize and enhance link prediction, arXiv:2103.11414,","author":"Wu","year":"2022"},{"key":"2026051811065224800_ref50","doi-asserted-by":"crossref","DOI":"10.1140\/epjb\/s10051-023-00495-1","article-title":"Graph attention network via node similarity for link prediction","volume":"96","author":"Yang","year":"2023","journal-title":"Eur Phys J B"},{"key":"2026051811065224800_ref51","doi-asserted-by":"crossref","first-page":"112965","DOI":"10.1016\/j.asoc.2025.112965","article-title":"LOSS-GAT: Label propagation and one-class semi-supervised graph attention network for fake news detection","volume":"174","author":"Lakzaei","year":"2025","journal-title":"Appl Soft Comput"},{"key":"2026051811065224800_ref52","doi-asserted-by":"crossref","first-page":"e2025581118","DOI":"10.1073\/pnas.2025581118","article-title":"Network medicine framework for identifying drug-repurposing opportunities for covid-19","volume":"118","author":"Gysi","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2026051811065224800_ref53","doi-asserted-by":"crossref","DOI":"10.1109\/ICDE55515.2023.00379","article-title":"Knowledge graph embedding based on graph neural network","volume-title":"2023 IEEE 39th International Conference on Data Engineering (ICDE), Anaheim, California, USA, April","author":"Liang","year":"2023"},{"key":"2026051811065224800_ref54","article-title":"Heterophily-aware fair recommendation using graph convolutional networks","author":"Gholinejad","year":"2024"},{"key":"2026051811065224800_ref55","volume-title":"Graph Recurrent Networks. Introduction to Graph Neural Networks","author":"Liu"},{"key":"2026051811065224800_ref56","author":"PyTorch Contributors","year":"2022"},{"key":"2026051811065224800_ref57","doi-asserted-by":"crossref","first-page":"370","DOI":"10.2307\/2344614","article-title":"Generalized linear models","volume":"135","author":"Nelder","year":"1972","journal-title":"J R Stat Soc A"},{"key":"2026051811065224800_ref58","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J R Stat Soc B Methodol"},{"key":"2026051811065224800_ref59","article-title":"Supervised data mining in networks: link prediction and applications","author":"G\u00f3mez-Mart\u00ednez","year":"2018"},{"key":"2026051811065224800_ref60","doi-asserted-by":"crossref","DOI":"10.5220\/0005610103160321","article-title":"The noesis open source framework for network data mining","volume-title":"2015 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K)","author":"Mart\u00ednez","year":"2015"},{"key":"2026051811065224800_ref61","first-page":"1343","article-title":"KONECT: the Koblenz network collection","volume-title":"22nd International World Wide Web Conference, WWW \u201813, May 13\u201317, 2013, Companion Volume, Rio de Janeiro, Brazil, May","author":"Kunegis","year":"2013"},{"key":"2026051811065224800_ref62","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, June 19\u201324, 2016, New York, NY, USA, June, JMLR Workshop and Conference Proceedings","author":"Yang","year":"2016"},{"key":"2026051811065224800_ref63","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9277","volume-title":"The Network Data Repository with Interactive Graph Analytics and Visualization","author":"Rossi","year":"2015"},{"key":"2026051811065224800_ref64","doi-asserted-by":"crossref","first-page":"125783","DOI":"10.1016\/j.physa.2021.125783","article-title":"Biased random walk with restart for link prediction with graph embedding method","volume":"570","author":"Zhou","year":"2021","journal-title":"Physica A Stat Mech Appl"},{"key":"2026051811065224800_ref65","article-title":"torch.nn.elu.","author":"PyTorch Contributors","year":"2022"},{"key":"2026051811065224800_ref66","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2026051811065224800_ref67","volume-title":"Collection of Simple Pytorch Implementations of Neural Networks and Related Algorithms","author":"LabML"},{"key":"2026051811065224800_ref68","volume-title":"Fast Graph Representation Learning with PyTorch Geometric","author":"Fey","year":"2019"},{"key":"2026051811065224800_ref69","article-title":"Dynamical algorithms for data mining and machine learning over dynamic graphs","volume":"11","author":"Chehreghani","year":"2021","journal-title":"WIREs Data Mining Knowl Discov"},{"key":"2026051811065224800_ref70","first-page":"23083","article-title":"Hierarchical correlation clustering and tree preserving embedding","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024, Seattle, WA, USA, June 16-22, 2024","author":"Chehreghani","year":"2024"},{"key":"2026051811065224800_ref71","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.1007\/s10994-020-05895-3","article-title":"Learning representations from dendrograms","volume":"109","author":"Chehreghani","year":"2020","journal-title":"Mach Learn"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/5\/773\/66675889\/bxaf144.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/69\/5\/773\/66675889\/bxaf144.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T15:07:09Z","timestamp":1779116829000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/69\/5\/773\/8450227"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":71,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,1,31]]},"published-print":{"date-parts":[[2026,5,16]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf144","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,1,31]]}}}