{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:11:04Z","timestamp":1774721464453,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709268","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"625-635","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Simplicial SMOTE: Oversampling Solution to the Imbalanced Learning Problem"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7679-755X","authenticated-orcid":false,"given":"Oleg","family":"Kachan","sequence":"first","affiliation":[{"name":"Sber AI Lab, Moscow, Russian Federation & HSE University, Moscow, Russian Federation"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6196-0564","authenticated-orcid":false,"given":"Andrey","family":"Savchenko","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russian Federation & HSE University, Moscow, Russian Federation"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7298-1848","authenticated-orcid":false,"given":"Gleb","family":"Gusev","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russian Federation"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2012.232"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007730.1007735"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3219934"},{"key":"e_1_3_2_2_4_1","volume-title":"Geometric and topological inference","author":"Boissonnat Jean-Daniel","unstructured":"\u00a0Jean-Daniel Boissonnat, Fr\u00e9d\u00e9ric Chazal, and Mariette Yvinec. 2018. Geometric and topological inference. Vol. 57. Cambridge University Press."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-011-0287-y"},{"key":"e_1_3_2_2_7_1","volume-title":"Vicinal risk minimization. Advances in Neural Information Processing Systems 13","author":"Chapelle Olivier","year":"2000","unstructured":"\u00a0Olivier Chapelle, Jason Weston, L\u00e9on Bottou, and Vladimir Vapnik. 2000. Vicinal risk minimization. Advances in Neural Information Processing Systems 13 (2000)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10759-6"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/0214017"},{"key":"e_1_3_2_2_11_1","volume-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics 21","author":"Chicco Davide","year":"2020","unstructured":"\u00a0Davide Chicco and Giuseppe Jurman. 2020. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics 21 (2020), 1--13."},{"key":"e_1_3_2_2_12_1","volume-title":"Proceedings of European Symposium on Artificial Neural Networks (ESANN). 503--508","author":"Vries Harm De","year":"2016","unstructured":"\u00a0Harm De Vries, Roland Memisevic, and Aaron Courville. 2016. Deep Learning Vector Quantization. In Proceedings of European Symposium on Artificial Neural Networks (ESANN). 503--508."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_2_2_14_1","volume-title":"Computational topology for data analysis","author":"Dey Tamal Krishna","unstructured":"\u00a0Tamal Krishna Dey and Yusu Wang. 2022. Computational topology for data analysis. Cambridge University Press."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2543629"},{"key":"e_1_3_2_2_16_1","volume-title":"Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD)","volume":"96","author":"Ester Martin","year":"1996","unstructured":"\u00a0Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD), Vol. 96. 226--231."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1154-8"},{"key":"e_1_3_2_2_19_1","volume-title":"IEEE International Joint Conference on Neural Networks. IEEE, 1322--1328","author":"He Haibo","year":"2008","unstructured":"\u00a0Haibo He, Yang Bai, Edwardo Garcia, and Shutao Li. 2008. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In IEEE International Joint Conference on Neural Networks. IEEE, 1322--1328."},{"key":"e_1_3_2_2_20_1","first-page":"1727","article-title":"Neighbourhoods, Classes and Near Sets","volume":"5","author":"Henry Christopher","year":"2011","unstructured":"\u00a0Christopher Henry. 2011. Neighbourhoods, Classes and Near Sets. Applied Mathematical Sciences 5, 35 (2011), 1727--1732.","journal-title":"Applied Mathematical Sciences"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00436"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.100"},{"key":"e_1_3_2_2_23_1","volume-title":"Improved precision and recall metric for assessing generative models. Advances in Neural Information Processing Systems 32","author":"Kynk\u00e4\u00e4nniemi Tuomas","year":"2019","unstructured":"\u00a0Tuomas Kynk\u00e4\u00e4nniemi, Tero Karras, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2019. Improved precision and recall metric for assessing generative models. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00043"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27810-8_23"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02760024"},{"key":"e_1_3_2_2_27_1","volume-title":"LVQ-SMOTE--learning vector quantization based synthetic minority over-sampling technique for biomedical data. BioData mining 6, 1","author":"Nakamura Munehiro","year":"2013","unstructured":"Munehiro Nakamura, Yusuke Kajiwara, Atsushi Otsuka, and Haruhiko Kimura. 2013. LVQ-SMOTE--learning vector quantization based synthetic minority over-sampling technique for biomedical data. BioData mining 6, 1 (2013), 1--10."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1504\/IJKESDP.2011.039875"},{"key":"e_1_3_2_2_29_1","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","author":"Pedregosa Fabian","year":"2011","unstructured":"Fabian Pedregosa, Ga\u00ebl Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12, Oct (2011), 2825--2830.","journal-title":"Journal of Machine Learning Research 12"},{"key":"e_1_3_2_2_30_1","volume-title":"CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems 31","author":"Prokhorenkova Liudmila","year":"2018","unstructured":"Liudmila Prokhorenkova, Gleb Gusev, Aleksandr Vorobev, Anna-Veronika Dorogush, and Andrey Gulin. 2018. CatBoost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_2_31_1","volume-title":"A Note on the Simplex-Tree Construction of the Vietoris-Rips Complex. arXiv preprint arXiv:2301.07191","author":"Rieser Antonio","year":"2023","unstructured":"Antonio Rieser. 2023. A Note on the Simplex-Tree Construction of the Vietoris-Rips Complex. arXiv preprint arXiv:2301.07191 (2023)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.171"},{"key":"e_1_3_2_2_33_1","volume-title":"Search techniques in intelligent classification systems","author":"Savchenko Andrey V","unstructured":"Andrey V Savchenko. 2016. Search techniques in intelligent classification systems. Springer."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CICN51697.2021.9574668"},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of 11th International Conference on Data Mining (ICDM). IEEE, 754--763","author":"Wallace Byron C","unstructured":"Byron C Wallace, Kevin Small, Carla E Brodley, and Thomas A Trikalinos.2011. Class imbalance, redux. In Proceedings of 11th International Conference on Data Mining (ICDM). IEEE, 754--763."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2985965"},{"key":"e_1_3_2_2_38_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2010.03.007"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709268","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:42:36Z","timestamp":1755358956000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":39,"alternative-id":["10.1145\/3690624.3709268","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709268","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}