{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T11:19:42Z","timestamp":1771672782138,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100009567","name":"Budapest University of Technology and Economics","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009567","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Network science has witnessed a surge in popularity, driven by the transformative power of node representation learning for diverse applications like social network analysis and biological modeling. While shallow embedding algorithms excel at capturing network structure, they face a critical limitation\u2014failing to generalize to unseen nodes. This paper addresses this challenge by introducing Inductive Shallow Node Embedding\u2014as a main contribution\u2014pioneering a novel approach that extends shallow embeddings to the realm of inductive learning. It has a novel encoder architecture that captures the local neighborhood structure of each node, enabling effective generalization to unseen nodes. In the generalization, robustness is essential to avoid degradation of performance arising from noise in the dataset. It has been theoretically proven that the covariance of the additive noise term in the proposed model is inversely proportional to the cardinality of a node\u2019s neighbors. Another contribution is a mathematical lower bound to quantify the robustness of node embeddings, confirming its advantage over traditional shallow embedding methods, particularly in the presence of parameter noise. The proposed method demonstrably excels in dynamic networks, consistently achieving over 90% performance on previously unseen nodes compared to nodes encountered during training on various benchmarks. The empirical evaluation concludes that our method outperforms competing methods on the vast majority of datasets in both transductive and inductive tasks.<\/jats:p>","DOI":"10.1007\/s40747-024-01545-6","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T05:02:04Z","timestamp":1720760524000},"page":"7333-7348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised Graph Representation Learning with Inductive Shallow Node Embedding"],"prefix":"10.1007","volume":"10","author":[{"given":"Rich\u00e1rd","family":"Kiss","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5781-1088","authenticated-orcid":false,"given":"G\u00e1bor","family":"Sz\u0171cs","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"1545_CR1","unstructured":"Hamilton WL, Ying R, Leskovec J (2017) Representation learning on graphs: methods and applications. arXiv preprint arXiv:1709.05584"},{"issue":"1","key":"1545_CR2","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1093\/bib\/bbab340","volume":"23","author":"H-C Yi","year":"2022","unstructured":"Yi H-C, You Z-H, Huang D-S, Kwoh CK (2022) Graph representation learning in bioinformatics: trends, methods and applications. Briefings Bioinform 23(1):340","journal-title":"Briefings Bioinform"},{"key":"1545_CR3","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s12859-018-2070-0","volume":"19","author":"M Kim","year":"2018","unstructured":"Kim M, Baek SH, Song M (2018) Relation extraction for biological pathway construction using node2vec. BMC Bioinform 19:75\u201384","journal-title":"BMC Bioinform"},{"issue":"1","key":"1545_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-021-00552-w","volume":"13","author":"MA Thafar","year":"2021","unstructured":"Thafar MA, Olayan RS, Albaradei S, Bajic VB, Gojobori T, Essack M, Gao X (2021) Dti2vec: drug-target interaction prediction using network embedding and ensemble learning. J Cheminform 13(1):1\u201318","journal-title":"J Cheminform"},{"key":"1545_CR5","doi-asserted-by":"crossref","unstructured":"Wang Y, Li Z, Farimani AB (2023) In: Qu, C., Liu, H. (eds.) Graph neural networks for molecules, pp. 21\u201366. Springer, Cham","DOI":"10.1007\/978-3-031-37196-7_2"},{"key":"1545_CR6","doi-asserted-by":"crossref","unstructured":"Wang M, Lin Y, Lin G, Yang K, Wu X-m (2020) M2grl: A multi-task multi-view graph representation learning framework for web-scale recommender systems. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2349\u20132358","DOI":"10.1145\/3394486.3403284"},{"key":"1545_CR7","doi-asserted-by":"crossref","unstructured":"Ge S, Wu C, Wu F, Qi T, Huang Y (2020) Graph enhanced representation learning for news recommendation. In: Proceedings of The Web Conference 2020, pp. 2863\u20132869","DOI":"10.1145\/3366423.3380050"},{"key":"1545_CR8","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1007\/s00521-018-03964-2","volume":"32","author":"Y Liu","year":"2020","unstructured":"Liu Y, Tian Z, Sun J, Jiang Y, Zhang X (2020) Distributed representation learning via node2vec for implicit feedback recommendation. Neural Comput Appl 32:4335\u20134345","journal-title":"Neural Comput Appl"},{"key":"1545_CR9","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3389\/fdata.2019.00002","volume":"2","author":"Q Tan","year":"2019","unstructured":"Tan Q, Liu N, Hu X (2019) Deep representation learning for social network analysis. Front Big Data 2:2","journal-title":"Front Big Data"},{"issue":"21","key":"1545_CR10","doi-asserted-by":"publisher","first-page":"16647","DOI":"10.1007\/s00521-020-04908-5","volume":"32","author":"B Li","year":"2020","unstructured":"Li B, Pi D (2020) Network representation learning: a systematic literature review. Neural Comput Appl 32(21):16647\u201316679","journal-title":"Neural Comput Appl"},{"key":"1545_CR11","doi-asserted-by":"crossref","unstructured":"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, pp. 855\u2013864","DOI":"10.1145\/2939672.2939754"},{"key":"1545_CR12","doi-asserted-by":"publisher","first-page":"101940","DOI":"10.1016\/j.jocs.2022.101940","volume":"67","author":"K Ljubi\u010di\u0107","year":"2023","unstructured":"Ljubi\u010di\u0107 K, Mer\u0107ep A, Kostanj\u010dar Z (2023) Churn prediction methods based on mutual customer interdependence. J Comput Sci 67:101940","journal-title":"J Comput Sci"},{"key":"1545_CR13","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.patrec.2022.04.036","volume":"159","author":"DC Thang","year":"2022","unstructured":"Thang DC, Dat HT, Tam NT, Jo J, Hung NQV, Aberer K (2022) Nature vs. nurture: feature vs. structure for graph neural networks. Pattern Recogn Lett 159:46\u201353","journal-title":"Pattern Recogn Lett"},{"key":"1545_CR14","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Adv Neural Inform Process Syst 30"},{"key":"1545_CR15","doi-asserted-by":"crossref","unstructured":"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, pp. 701\u2013710","DOI":"10.1145\/2623330.2623732"},{"key":"1545_CR16","doi-asserted-by":"crossref","unstructured":"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, pp. 1067\u20131077","DOI":"10.1145\/2736277.2741093"},{"key":"1545_CR17","doi-asserted-by":"crossref","unstructured":"Qiu J, Dong Y, Ma H, Li J, Wang K, Tang J (2018) Network embedding as matrix factorization: Unifying deepwalk, line, pte, and node2vec. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 459\u2013467","DOI":"10.1145\/3159652.3159706"},{"key":"1545_CR18","doi-asserted-by":"crossref","unstructured":"Cao S, Lu W, Xu Q (2015) Grarep: learning graph representations with global structural information. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 891\u2013900","DOI":"10.1145\/2806416.2806512"},{"key":"1545_CR19","doi-asserted-by":"crossref","unstructured":"Tang J, Qu M, Mei Q (2015) Pte: Predictive text embedding through large-scale heterogeneous text networks. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1165\u20131174","DOI":"10.1145\/2783258.2783307"},{"key":"1545_CR20","doi-asserted-by":"crossref","unstructured":"Guo L, Cai X, Qin H, Hao F, Guo S (2022) A content-sensitive citation representation approach for citation recommendation. J Ambient Intell Hum Comput:1\u201312","DOI":"10.1007\/s12652-021-03153-5"},{"key":"1545_CR21","doi-asserted-by":"publisher","first-page":"43378","DOI":"10.1109\/ACCESS.2021.3062467","volume":"9","author":"H Zhou","year":"2021","unstructured":"Zhou H, Sun G, Fu S, Wang L, Hu J, Gao Y (2021) Internet financial fraud detection based on a distributed big data approach with node2vec. IEEE Access 9:43378\u201343386","journal-title":"IEEE Access"},{"issue":"2","key":"1545_CR22","doi-asserted-by":"publisher","first-page":"1257","DOI":"10.1109\/TCBB.2022.3191972","volume":"20","author":"J Ha","year":"2022","unstructured":"Ha J, Park S (2022) Ncmd: Node2vec-based neural collaborative filtering for predicting mirna-disease association. IEEE\/ACM Trans Comput Biol Bioinform 20(2):1257\u20131268","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"1545_CR23","doi-asserted-by":"publisher","first-page":"6658","DOI":"10.1038\/s41598-020-63735-9","volume":"10","author":"B-Y Ji","year":"2020","unstructured":"Ji B-Y, You Z-H, Cheng L, Zhou J-R, Alghazzawi D, Li L-P (2020) Predicting mirna-disease association from heterogeneous information network with grarep embedding model. Sci Rep 10(1):6658","journal-title":"Sci Rep"},{"issue":"8","key":"1545_CR24","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.1007\/s00521-023-09286-2","volume":"36","author":"X Liang","year":"2024","unstructured":"Liang X, Si G, Li J, Tian P, An Z, Zhou F (2024) A survey of inductive knowledge graph completion. Neural Comput Appl 36(8):3837\u20133858","journal-title":"Neural Comput Appl"},{"key":"1545_CR25","doi-asserted-by":"crossref","unstructured":"Tran DH, Sheng QZ, Zhang WE, Aljubairy A, Zaib M, Hamad SA, Tran NH, Khoa NLD (2021) Hetegraph: graph learning in recommender systems via graph convolutional networks. Neural Comput Appl:1\u201317","DOI":"10.1109\/IJCNN48605.2020.9207078"},{"key":"1545_CR26","doi-asserted-by":"crossref","unstructured":"Lo WW, Layeghy S, Sarhan M, Gallagher M, Portmann M (2022) E-graphsage: a graph neural network based intrusion detection system for iot. In: NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium, pp. 1\u20139. IEEE","DOI":"10.1109\/NOMS54207.2022.9789878"},{"key":"1545_CR27","doi-asserted-by":"publisher","first-page":"106524","DOI":"10.1016\/j.compbiomed.2022.106524","volume":"153","author":"J Liu","year":"2023","unstructured":"Liu J, Lei X, Zhang Y, Pan Y (2023) The prediction of molecular toxicity based on bigru and graphsage. Comput Biol Med 153:106524","journal-title":"Comput Biol Med"},{"key":"1545_CR28","doi-asserted-by":"publisher","first-page":"122027","DOI":"10.1016\/j.eswa.2023.122027","volume":"238","author":"Q Sun","year":"2024","unstructured":"Sun Q, Wei X, Yang X (2024) Graphsage with deep reinforcement learning for financial portfolio optimization. Expert Syst Appl 238:122027","journal-title":"Expert Syst Appl"},{"issue":"3","key":"1545_CR29","doi-asserted-by":"publisher","first-page":"1755","DOI":"10.1109\/TITS.2020.3026025","volume":"23","author":"J Liu","year":"2020","unstructured":"Liu J, Ong GP, Chen X (2020) Graphsage-based traffic speed forecasting for segment network with sparse data. IEEE Trans Intell Transp Syst 23(3):1755\u20131766","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1545_CR30","first-page":"22118","volume":"33","author":"W Hu","year":"2020","unstructured":"Hu W, Fey M, Zitnik M, Dong Y, Ren H, Liu B, Catasta M, Leskovec J (2020) Open graph benchmark: datasets for machine learning on graphs. Adv Neural Inform Process Syst 33:22118\u201322133","journal-title":"Adv Neural Inform Process Syst"},{"key":"1545_CR31","unstructured":"Bojchevski A, G\u00fcnnemann S (2017) Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. arXiv preprint arXiv:1707.03815"},{"key":"1545_CR32","doi-asserted-by":"crossref","unstructured":"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\u2013826","DOI":"10.1145\/1557019.1557109"},{"key":"1545_CR33","unstructured":"Mernyei P, Cangea C (2020) Wiki-cs: A wikipedia-based benchmark for graph neural networks. arXiv preprint arXiv:2007.02901"},{"issue":"4","key":"1545_CR34","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1209\/epl\/i2003-00166-9","volume":"61","author":"H Jeong","year":"2003","unstructured":"Jeong H, N\u00e9da Z, Barab\u00e1si A-L (2003) Measuring preferential attachment in evolving networks. Europhys Lett 61(4):567","journal-title":"Europhys Lett"},{"issue":"6","key":"1545_CR35","doi-asserted-by":"publisher","first-page":"061815","DOI":"10.1117\/1.JEI.31.6.061815","volume":"31","author":"M Bukumira","year":"2022","unstructured":"Bukumira M, Antonijevic M, Jovanovic D, Zivkovic M, Mladenovic D, Kunjadic G (2022) Carrot grading system using computer vision feature parameters and a cascaded graph convolutional neural network. J Electron Imaging 31(6):061815\u2013061815","journal-title":"J Electron Imaging"},{"issue":"4","key":"1545_CR36","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1038\/s42256-022-00468-6","volume":"4","author":"MJ Schuetz","year":"2022","unstructured":"Schuetz MJ, Brubaker JK, Katzgraber HG (2022) Combinatorial optimization with physics-inspired graph neural networks. Nat Mach Intell 4(4):367\u2013377","journal-title":"Nat Mach Intell"},{"key":"1545_CR37","unstructured":"Tolstaya E, Gama F, Paulos J, Pappas G, Kumar V, Ribeiro A (2020) Learning decentralized controllers for robot swarms with graph neural networks. In: Conference on Robot Learning, pp. 671\u2013682. PMLR"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01545-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-024-01545-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-024-01545-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,14]],"date-time":"2024-09-14T15:27:22Z","timestamp":1726327642000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-024-01545-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":37,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1545"],"URL":"https:\/\/doi.org\/10.1007\/s40747-024-01545-6","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]},"assertion":[{"value":"26 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}