{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T02:01:15Z","timestamp":1770516075964,"version":"3.49.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T00:00:00Z","timestamp":1767484800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s11222-025-10811-7","type":"journal-article","created":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T02:28:46Z","timestamp":1767493726000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Resolving data imbalance in transfer learning: a simple random sampling approach"],"prefix":"10.1007","volume":"36","author":[{"given":"Andrei","family":"Afilipoaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Venkata Shreya","family":"Kala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jainish","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ce","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linglong","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,4]]},"reference":[{"key":"10811_CR1","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1007\/978-3-540-27868-9_76","volume-title":"Structural, Syntactic, and Statistical Pattern Recognition","author":"H Alt\u0131n\u00e7ay","year":"2004","unstructured":"Alt\u0131n\u00e7ay, H., Erg\u00fcn, C.: Clustering based under-sampling for improving speaker verification decisions using adaboost. In: Fred, A., Caelli, T.M., Duin, R.P.W., Campilho, A.C., Ridder, D. (eds.) Structural, Syntactic, and Statistical Pattern Recognition, pp. 698\u2013706. Springer, Berlin, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-27868-9_76"},{"issue":"3","key":"10811_CR2","doi-asserted-by":"publisher","first-page":"36738","DOI":"10.7759\/cureus.36738","volume":"15","author":"KS Alwadeai","year":"2023","unstructured":"Alwadeai, K.S., Almeshari, M.A., Alghamdi, A.S., Alshehri, A.M., Alsaif, S.S., Al-Heizan, M.O., Alwadei, M.S., Alahmari, A.D., Algarni, S.S., Alotaibi, T.F., Alqahtani, M.M., Alqahtani, N., Alqahtani, J.S., Aldhahir, A.M., Homoud, M.M., Alhammad, S.A.: Relationship between heart disease and obesity indicators among adults: a secondary data analysis. Cureus 15(3), 36738 (2023). https:\/\/doi.org\/10.7759\/cureus.36738","journal-title":"Cureus"},{"issue":"1","key":"10811_CR3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1006\/jmaa.1998.6252","volume":"234","author":"H Alzer","year":"1999","unstructured":"Alzer, H.: On the Cauchy-Schwarz Inequality. J. Math. Anal. Appl. 234(1), 6\u201314 (1999). https:\/\/doi.org\/10.1006\/jmaa.1998.6252","journal-title":"J. Math. Anal. Appl."},{"key":"10811_CR4","doi-asserted-by":"publisher","unstructured":"Arnold, A., Nallapati, R., Cohen, W.W.: A comparative study of methods for transductive transfer learning. In: Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007), pp. 77\u201382 (2007). https:\/\/doi.org\/10.1109\/ICDMW.2007.109","DOI":"10.1109\/ICDMW.2007.109"},{"issue":"4","key":"10811_CR5","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.3390\/molecules28041663","volume":"28","author":"AK Azlim\u00a0Khan","year":"2023","unstructured":"Azlim\u00a0Khan, A.K., Ahamed Hassain\u00a0Malim, N.H.: Comparative studies on resampling techniques in machine learning and deep learning models for drug-target interaction prediction. Molecules 28(4), 1663 (2023). https:\/\/doi.org\/10.3390\/molecules28041663","journal-title":"Molecules"},{"key":"10811_CR6","doi-asserted-by":"publisher","first-page":"13588","DOI":"10.24432\/C5XW20","volume":"13","author":"B Becker","year":"1996","unstructured":"Becker, B., Kohavi, R.: Adult. UCI Mach. Learn. Repos. 13, 13588 (1996). https:\/\/doi.org\/10.24432\/C5XW20","journal-title":"UCI Mach. Learn. Repos."},{"issue":"3","key":"10811_CR7","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1111\/rssb.12368","volume":"82","author":"G Chauvet","year":"2020","unstructured":"Chauvet, G., Vall\u00e9e, A.-A.: Inference for two-stage sampling designs. J. R. Stat. Soc. Ser. B Stat Methodol. 82(3), 797\u2013815 (2020). https:\/\/doi.org\/10.1111\/rssb.12368","journal-title":"J. R. Stat. Soc. Ser. B Stat Methodol."},{"key":"10811_CR8","volume-title":"Sampling Techniques","author":"WG Cochran","year":"1977","unstructured":"Cochran, W.G.: Sampling Techniques, 3rd edn. Wiley, Hoboken, NJ, USA (1977)","edition":"3"},{"issue":"6","key":"10811_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/wics.1414","volume":"9","author":"A ElRafey","year":"2017","unstructured":"ElRafey, A., Wojtusiak, J.: Recent advances in scaling-down sampling methods in machine learning. Wiley Int. Rev. Comput. Stat. 9(6), e1414 (2017). https:\/\/doi.org\/10.1002\/wics.1414","journal-title":"Wiley Int. Rev. Comput. Stat."},{"issue":"5","key":"10811_CR10","doi-asserted-by":"publisher","first-page":"1232","DOI":"10.3390\/nu15051232","volume":"15","author":"JW Horn","year":"2023","unstructured":"Horn, J.W., Feng, T., M\u00f8rkedal, B., Aune, D., Strand, L.B., Horn, J., Mukamal, K.J., Janszky, I.: Body mass index measured repeatedly over 42 years as a risk factor for ischemic stroke: the HUNT study. Nutrients 15(5), 1232 (2023). https:\/\/doi.org\/10.3390\/nu15051232","journal-title":"Nutrients"},{"issue":"1","key":"10811_CR11","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1186\/s40537-022-00652-w","volume":"9","author":"A Hosna","year":"2022","unstructured":"Hosna, A., Merry, E., Gyalmo, J., Alom, Z., Aung, Z., Azim, M.A.: Transfer learning: a friendly introduction. J. Big Data 9(1), 102 (2022). https:\/\/doi.org\/10.1186\/s40537-022-00652-w","journal-title":"J. Big Data"},{"issue":"1","key":"10811_CR12","doi-asserted-by":"publisher","first-page":"00090","DOI":"10.15406\/iratj.2018.04.00090","volume":"4","author":"MA Khaldy","year":"2018","unstructured":"Khaldy, M.A., Kambhampati, C.: Resampling imbalanced class and the effectiveness of feature selection methods for heart failure dataset. Int. Robot. Auto. J. 4(1), 00090 (2018). https:\/\/doi.org\/10.15406\/iratj.2018.04.00090","journal-title":"Int. Robot. Auto. J."},{"key":"10811_CR13","unstructured":"Krizhevsky, A.: CIFAR-10 and CIFAR-100 datasets. Retrieved October 25, 2025, from https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html (2009a)"},{"key":"10811_CR14","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report, University of Toronto. https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf (2009b)"},{"key":"10811_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105621","volume":"117","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Yang, G., Qiao, S., Liu, M., Qu, L., Han, N., Wu, T., Yuan, G., Wu, T., Peng, Y.: Imbalanced data classification: using transfer learning and active sampling. Eng. Appl. Artif. Intell. 117, 105621 (2023). https:\/\/doi.org\/10.1016\/j.engappai.2022.105621","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10811_CR16","unstructured":"Lu, C., Wu, Y., Hern\u00e1ndez-Lobato, J.M., Sch\u00f6lkopf, B.: Invariant causal representation learning for out-of-distribution generalization. In: International Conference on Learning Representations (2022)"},{"key":"10811_CR17","doi-asserted-by":"crossref","unstructured":"Lv, F., Liang, J., Li, S., Zang, B., Liu, C.H., Wang, Z., Liu, D.: Causality inspired representation learning for domain generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8046\u20138056 (2022)","DOI":"10.1109\/CVPR52688.2022.00788"},{"key":"10811_CR18","doi-asserted-by":"publisher","unstructured":"McCarthy, K., Zabar, B., Weiss, G.: Does cost-sensitive learning beat sampling for classifying rare classes? In: UBDM \u201905: Proceedings of the 1st International Workshop on Utility-Based Data Mining, pp. 69\u201377. Association for Computing Machinery, New York, NY, USA (2005). https:\/\/doi.org\/10.1145\/1089827.1089836","DOI":"10.1145\/1089827.1089836"},{"key":"10811_CR19","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/s10618-012-0295-5","volume":"28","author":"G Menardi","year":"2014","unstructured":"Menardi, G., Torelli, N.: Training and assessing classification rules with imbalanced data. Data Min. Knowl. Disc. 28, 92\u2013122 (2014). https:\/\/doi.org\/10.1007\/s10618-012-0295-5","journal-title":"Data Min. Knowl. Disc."},{"key":"10811_CR20","doi-asserted-by":"publisher","DOI":"10.24432\/C5K306","author":"S Moro","year":"2014","unstructured":"Moro, S., Rita, P., Cortez, P.: Bank marketing. UCI Mach. Learn. Repos. (2014). https:\/\/doi.org\/10.24432\/C5K306","journal-title":"UCI Mach. Learn. Repos."},{"issue":"10","key":"10811_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010). https:\/\/doi.org\/10.1109\/TKDE.2009.191","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"1","key":"10811_CR22","first-page":"237","volume":"2014","author":"N Poolsawad","year":"2014","unstructured":"Poolsawad, N., Kambhampati, C., Cleland, J.G.F.: Balancing class for performance of classification with a clinical dataset. Proc. World Congress on Eng. 2014(1), 237\u2013242 (2014)","journal-title":"Proc. World Congress on Eng."},{"key":"10811_CR23","unstructured":"Rahman, M.M., Davis, D.N.: Cluster based under-sampling for unbalanced cardiovascular data. 3, (2013)"},{"issue":"5","key":"10811_CR24","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","volume":"109","author":"B Sch\u00f6lkopf","year":"2021","unstructured":"Sch\u00f6lkopf, B., Locatello, F., Bauer, S., Ke, N.R., Kalchbrenner, N., Goyal, A., Bengio, Y.: Toward causal representation learning. Proc. IEEE 109(5), 612\u2013634 (2021). https:\/\/doi.org\/10.1109\/JPROC.2021.3058954","journal-title":"Proc. IEEE"},{"key":"10811_CR25","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","volume-title":"Artificial Neural Networks and Machine Learning - ICANN 2018","author":"C Tan","year":"2018","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) Artificial Neural Networks and Machine Learning - ICANN 2018, pp. 270\u2013279. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01424-7_27"},{"key":"10811_CR26","doi-asserted-by":"publisher","DOI":"10.24432\/C53919","author":"A Teboul","year":"2023","unstructured":"Teboul, A.: CDC diabetes health indicators. UCI Mach. Learn. Repos. (2023). https:\/\/doi.org\/10.24432\/C53919","journal-title":"UCI Mach. Learn. Repos."},{"key":"10811_CR27","doi-asserted-by":"publisher","first-page":"196197","DOI":"10.1109\/ACCESS.2020.3034343","volume":"8","author":"G Vrban\u010di\u010d","year":"2020","unstructured":"Vrban\u010di\u010d, G., Podgorelec, V.: Transfer learning with adaptive fine-tuning. IEEE Access 8, 196197\u2013196211 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3034343","journal-title":"IEEE Access"},{"key":"10811_CR28","doi-asserted-by":"publisher","first-page":"6279","DOI":"10.1007\/s00415-022-11318-1","volume":"269","author":"X Wang","year":"2022","unstructured":"Wang, X., Huang, Y., Chen, Y., Yang, T., Su, W., Chen, X., Yan, F., Han, L., Ma, Y.: The relationship between body mass index and stroke: a systemic review and meta-analysis. J. Neurol. 269, 6279\u20136289 (2022). https:\/\/doi.org\/10.1007\/s00415-022-11318-1","journal-title":"J. Neurol."},{"issue":"1","key":"10811_CR29","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3(1), 9 (2016). https:\/\/doi.org\/10.1186\/s40537-016-0043-6","journal-title":"J. Big Data"},{"issue":"1","key":"10811_CR30","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/info14010054","volume":"14","author":"T Wongvorachan","year":"2023","unstructured":"Wongvorachan, T., He, S., Bulut, O.: A comparison of undersampling, oversampling, and SMOTE methods for dealing with imbalanced classification in educational data mining. Inform. 14(1), 54 (2023). https:\/\/doi.org\/10.3390\/info14010054","journal-title":"Inform."},{"issue":"401","key":"10811_CR31","doi-asserted-by":"publisher","first-page":"150","DOI":"10.2307\/2288934","volume":"83","author":"CFJ Wu","year":"1988","unstructured":"Wu, C.F.J., Holt, D., Holmes, D.J.: The effect of two-stage sampling on the F statistic. J. Am. Stat. Assoc. 83(401), 150\u2013159 (1988). https:\/\/doi.org\/10.2307\/2288934","journal-title":"J. Am. Stat. Assoc."},{"key":"10811_CR32","unstructured":"Yang, Z., Yu, Y., You, C., Steinhardt, J., Ma, Y.: Rethinking bias-variance trade-off for generalization of neural networks. In: Daum\u00e9, H., III., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 10767\u201310777 (2020)"},{"key":"10811_CR33","doi-asserted-by":"publisher","DOI":"10.24432\/C55S3H","author":"I-C Yeh","year":"2009","unstructured":"Yeh, I.-C.: Default of credit card clients. UCI Mach. Learn. Repos. (2009). https:\/\/doi.org\/10.24432\/C55S3H","journal-title":"UCI Mach. Learn. Repos."},{"key":"10811_CR34","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/11823728_41","volume-title":"Data Warehousing and Knowledge Discovery","author":"S-J Yen","year":"2006","unstructured":"Yen, S.-J., Lee, Y.-S.: Cluster-based sampling approaches to imbalanced data distributions. In: Tjoa, A.M., Trujillo, J. (eds.) Data Warehousing and Knowledge Discovery, pp. 427\u2013436. Springer, Berlin, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11823728_41"},{"key":"10811_CR35","doi-asserted-by":"publisher","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? Adv. Neural Inf. Process. Syst. 27, (2014). https:\/\/doi.org\/10.48550\/arXiv.1411.1792","DOI":"10.48550\/arXiv.1411.1792"},{"key":"10811_CR36","doi-asserted-by":"publisher","unstructured":"Zadrozny, B.: Learning and evaluating classifiers under sample selection bias. In: 21st International Conference on Machine Learning, pp. 114. Association for Computing Machinery, New York, NY, USA (2004). https:\/\/doi.org\/10.1145\/1015330.1015425","DOI":"10.1145\/1015330.1015425"},{"issue":"1","key":"10811_CR37","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2021","unstructured":"Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., He, Q.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2021). https:\/\/doi.org\/10.1109\/JPROC.2020.3004555","journal-title":"Proc. IEEE"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10811-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-025-10811-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10811-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T03:54:06Z","timestamp":1770436446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-025-10811-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,4]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10811"],"URL":"https:\/\/doi.org\/10.1007\/s11222-025-10811-7","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"value":"0960-3174","type":"print"},{"value":"1573-1375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,4]]},"assertion":[{"value":"20 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2026","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 declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}],"article-number":"52"}}