{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T03:14:35Z","timestamp":1778037275521,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T00:00:00Z","timestamp":1763683200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T00:00:00Z","timestamp":1763683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100017691","name":"Guangxi Key Research and Development Program","doi-asserted-by":"publisher","award":["Gui Ke AB24010160"],"award-info":[{"award-number":["Gui Ke AB24010160"]}],"id":[{"id":"10.13039\/501100017691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62362015"],"award-info":[{"award-number":["62362015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of Guangxi Key Laboratory of Digital Infrastructure","award":["GXDIOP2024013"],"award-info":[{"award-number":["GXDIOP2024013"]}]},{"name":"Innovation Project of GUET Graduate Education","award":["2025YCXB009"],"award-info":[{"award-number":["2025YCXB009"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10844-025-01008-5","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T06:33:02Z","timestamp":1763706782000},"page":"445-468","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cardinality estimation with index-based progressive sampling and dynamic sample selection"],"prefix":"10.1007","volume":"64","author":[{"given":"Yan","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuming","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaojun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"You","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"key":"1008_CR1","doi-asserted-by":"publisher","unstructured":"Acharya, J., Diakonikolas, I., Hegde, C., et al. (2015) Fast and near-optimal algorithms for approximating distributions by histograms. PODS \u201915 (pp. 249\u2013263). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2745754.2745772","DOI":"10.1145\/2745754.2745772"},{"key":"1008_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Y., Yi, K. (2017). Two-level sampling for join size estimation. In Proceedings of the 2017 ACM International Conference on Management of Data. SIGMOD \u201917 (pp. 759\u2013774). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3035918.3035921","DOI":"10.1145\/3035918.3035921"},{"key":"1008_CR3","unstructured":"Cormen, T.H., Leiserson, C.E., Rivest, R.L., et al. (2022). Introduction to algorithms. MIT Press, Cambridge, MA . https:\/\/shorturl.asia\/budeU"},{"key":"1008_CR4","doi-asserted-by":"publisher","unstructured":"Dutt, A., Wang, C., Nazi, A., et al. (2019). Selectivity estimation for range predicates using lightweight models. Proceedings VLDB Endowment,12(9), 1044\u20131057. https:\/\/doi.org\/10.14778\/3329772.3329780","DOI":"10.14778\/3329772.3329780"},{"key":"1008_CR5","doi-asserted-by":"publisher","unstructured":"Flajolet, P., Fusy, \u00c9., Gandouet, O., et al.: Hyperloglog: the analysis of a near-optimal cardinality estimation algorithm. Discrete Mathematics & Theoretical Computer Science (Proceedings), (2007). https:\/\/doi.org\/10.46298\/dmtcs.3545","DOI":"10.46298\/dmtcs.3545"},{"key":"1008_CR6","doi-asserted-by":"publisher","unstructured":"Ganguly, S., Gibbons, P.B., Matias, Y., et al. (1996). Bifocal sampling for skew-resistant join size estimation. In Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data (pp. 271\u2013281). https:\/\/doi.org\/10.1145\/233269.233340","DOI":"10.1145\/233269.233340"},{"key":"1008_CR7","unstructured":"Gjurovski, D., Davitkova, A., & Michel, S. (2024). Grid-ar: a grid-based booster for learned cardinality estimation and range joins. https:\/\/arxiv.org\/abs\/2410.07895"},{"key":"1008_CR8","doi-asserted-by":"publisher","unstructured":"Hilprecht, B., Schmidt, A., Kulessa, M., et al. (2020). Deepdb: Learn from data, not from queries! Proceedings VLDB Endowment,13(7), 992\u20131005. https:\/\/doi.org\/10.14778\/3384345.3384349","DOI":"10.14778\/3384345.3384349"},{"key":"1008_CR9","doi-asserted-by":"publisher","unstructured":"Ioannidis, Y. (2003). The history of histograms (abridged). In Proceedings VLDB Endowment (pp. 19\u201330). https:\/\/doi.org\/10.1016\/B978-012722442-8\/50011-2","DOI":"10.1016\/B978-012722442-8\/50011-2"},{"issue":"2","key":"1008_CR10","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1111\/jtsa.12108","volume":"36","author":"L Kalliovirta","year":"2015","unstructured":"Kalliovirta, L., Meitz, M., & Saikkonen, P. (2015). A gaussian mixture autoregressive model for univariate time series. Journal of Time Series Analysis, 36(2), 247\u2013266. https:\/\/doi.org\/10.1111\/jtsa.12108","journal-title":"Journal of Time Series Analysis"},{"key":"1008_CR11","doi-asserted-by":"publisher","unstructured":"Kastrati, F., & Moerkotte, G. (2016). Optimization of conjunctive predicates for main memory column stores. Proceedings VLDB Endowment,9(12), 1125\u20131136. https:\/\/doi.org\/10.14778\/2994509.2994529","DOI":"10.14778\/2994509.2994529"},{"key":"1008_CR12","unstructured":"Kipf, A., Kipf, T., Radke, B., et al. (2018). Learned cardinalities: Estimating correlated joins with deep learning. https:\/\/arxiv.org\/abs\/1809.00677"},{"key":"1008_CR13","doi-asserted-by":"publisher","unstructured":"Lehmann, C., Sulimov, P., & Stockinger, K. (2024). Is your learned query optimizer behaving as you expect? a machine learning perspective. Proceedings VLDB Endowment,17(7), 1565\u20131577. https:\/\/doi.org\/10.14778\/3654621.3654625","DOI":"10.14778\/3654621.3654625"},{"key":"1008_CR14","doi-asserted-by":"publisher","unstructured":"Leis, V., Gubichev, A., Mirchev, A., et al. (2015). How good are query optimizers, really? Proceedings VLDB Endowment,9(3), 204\u2013215. https:\/\/doi.org\/10.14778\/2850583.2850594","DOI":"10.14778\/2850583.2850594"},{"key":"1008_CR15","unstructured":"Leis, V., Radke, B., Gubichev, A., et al. (2017). Cardinality estimation done right: Index-based join sampling. In CIDR. https:\/\/cidrdb.org\/cidr2017\/papers\/p9-leis-cidr17.pdf"},{"key":"1008_CR16","doi-asserted-by":"publisher","unstructured":"Li, P., Wei, W., Zhu, R., et al. (2023). Alece: An attention-based learned cardinality estimator for spj queries on dynamic workloads. Proceedings VLDB Endowment,17(2), 197\u2013210. https:\/\/doi.org\/10.14778\/3626292.3626302","DOI":"10.14778\/3626292.3626302"},{"issue":"4","key":"1008_CR17","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s41019-018-0074-4","volume":"3","author":"K Li","year":"2018","unstructured":"Li, K., & Li, G. (2018). Approximate query processing: What is new and where to go? a survey on approximate query processing. Data Science and Engineering, 3(4), 379\u2013397. https:\/\/doi.org\/10.1007\/s41019-018-0074-4","journal-title":"Data Science and Engineering"},{"key":"1008_CR18","doi-asserted-by":"publisher","unstructured":"Liu, J., Dong, W., Zhou, Q., et al. (2021). Fauce: Fast and accurate deep ensembles with uncertainty for cardinality estimation. Proceedings VLDB Endowment,14(11), 1950\u20131963 https:\/\/doi.org\/10.14778\/3476249.3476254","DOI":"10.14778\/3476249.3476254"},{"key":"1008_CR19","unstructured":"Malik, T., Burns, R.C., & Chawla, N.V. (2007). A black-box approach to query cardinality estimation. In CIDR (pp. 56\u201367). https:\/\/api.semanticscholar.org\/CorpusID:8005587"},{"key":"1008_CR20","doi-asserted-by":"publisher","unstructured":"M\u00fcller, M., Woltmann, L., & Lehner, W. (2023). Enhanced featurization of queries with mixed combinations of predicates for ml-based cardinality estimation. In EDBT (pp. 273\u2013284). https:\/\/doi.org\/10.48786\/edbt.2023.22","DOI":"10.48786\/edbt.2023.22"},{"key":"1008_CR21","unstructured":"Poosala, V., & Ioannidis, Y.E. (1997). Selectivity estimation without the attribute value independence assumption. In Proceedings VLDB Endowment (vol. 97, pp. 486\u2013495). https:\/\/api.semanticscholar.org\/CorpusID:8408623"},{"key":"1008_CR22","doi-asserted-by":"publisher","unstructured":"Qiu, Y., Wang, Y., Yi, K., et al. (2021). Weighted distinct sampling: cardinality estimation for spj queries. In Proceedings of the 2021 International Conference on Management of Data. SIGMOD \u201921 (pp. 1465\u20131477). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3448016.3452821","DOI":"10.1145\/3448016.3452821"},{"key":"1008_CR23","doi-asserted-by":"publisher","unstructured":"Sun, J., Zhang, J., Sun, Z., et al. (2021). Learned cardinality estimation: A design space exploration and a comparative evaluation. Proceedings VLDB Endowment,15(1), 85\u201397. https:\/\/doi.org\/10.14778\/3485450.3485459","DOI":"10.14778\/3485450.3485459"},{"key":"1008_CR24","doi-asserted-by":"publisher","unstructured":"To, H., Chiang, K., & Shahabi, C. (2013). Entropy-based histograms for selectivity estimation. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. CIKM \u201913 (pp. 1939\u20131948). Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2505515.2505756","DOI":"10.1145\/2505515.2505756"},{"issue":"14","key":"1008_CR25","doi-asserted-by":"publisher","first-page":"2775","DOI":"10.1016\/j.comnet.2013.05.011","volume":"57","author":"F Tschorsch","year":"2013","unstructured":"Tschorsch, F., & Scheuermann, B. (2013). An algorithm for privacy-preserving distributed user statistics. Computer Networks, 57(14), 2775\u20132787. https:\/\/doi.org\/10.1016\/j.comnet.2013.05.011","journal-title":"Computer Networks"},{"key":"1008_CR26","doi-asserted-by":"publisher","unstructured":"Vengerov, D., Menck, A.C., Zait, M., et al. (2015). Join size estimation subject to filter conditions. Proceedings VLDB Endowment,8(12), 1530\u20131541. https:\/\/doi.org\/10.14778\/2824032.2824051","DOI":"10.14778\/2824032.2824051"},{"key":"1008_CR27","doi-asserted-by":"publisher","unstructured":"Wang, T., & Chan, C.-Y. (2020). Improved correlated sampling for join size estimation. In 2020 IEEE 36th International Conference on Data Engineering (ICDE) (pp. 325\u2013336). https:\/\/doi.org\/10.1109\/ICDE48307.2020.00035","DOI":"10.1109\/ICDE48307.2020.00035"},{"key":"1008_CR28","doi-asserted-by":"publisher","unstructured":"Wang, J., Chai, C., Liu, J., et al. (2021). Face: A normalizing flow based cardinality estimator. Proceedings VLDB Endowment,15(1), 72\u201384. https:\/\/doi.org\/10.14778\/3485450.3485458","DOI":"10.14778\/3485450.3485458"},{"key":"1008_CR29","doi-asserted-by":"publisher","unstructured":"Wang, X., Qu, C., Wu, W., et al. (2021). Are we ready for learned cardinality estimation? Proceedings VLDB Endowment,14(9), 1640\u20131654. https:\/\/doi.org\/10.14778\/3461535.3461552","DOI":"10.14778\/3461535.3461552"},{"key":"1008_CR30","doi-asserted-by":"publisher","unstructured":"Wang, R.-A., Zou, Z., & Jing, Z. (2023). Cardinality estimation via learned dynamic sample selection. Information Systems,117, 102252. https:\/\/doi.org\/10.1016\/j.is.2023.102252","DOI":"10.1016\/j.is.2023.102252"},{"key":"1008_CR31","unstructured":"Wu, Z., Yu, P., Yang, P., et al. (2021). A unified transferable model for ml-enhanced dbms. https:\/\/arxiv.org\/abs\/2105.02418"},{"key":"1008_CR32","doi-asserted-by":"publisher","unstructured":"Xu, J., Zhang, Z., Xiao, X., et al. (2013). Differentially private histogram publication. Proceedings VLDB Endowment,22, 797\u2013822. https:\/\/doi.org\/10.1007\/s00778-013-0309-y","DOI":"10.1007\/s00778-013-0309-y"},{"key":"1008_CR33","doi-asserted-by":"publisher","unstructured":"Yang, Z., Kamsetty, A., Luan, S., et al. (2020). Neurocard: One cardinality estimator for all tables. Proceedings VLDB Endowment,14(1), 61\u201373. https:\/\/doi.org\/10.14778\/3421424.3421432","DOI":"10.14778\/3421424.3421432"},{"key":"1008_CR34","doi-asserted-by":"publisher","unstructured":"Yang, Z., Liang, E., Kamsetty, A., et al. (2020). Deep unsupervised cardinality estimation. Proceedings VLDB Endowment,13(3), 279\u2013292. https:\/\/doi.org\/10.14778\/3368289.3368294","DOI":"10.14778\/3368289.3368294"},{"key":"1008_CR35","doi-asserted-by":"publisher","unstructured":"Zhou, X., Sun, J., Li, G., et al. (2020). Query performance prediction for concurrent queries using graph embedding. Proceedings VLDB Endowment,13(9), 1416\u20131428. https:\/\/doi.org\/10.14778\/3397230.3397238","DOI":"10.14778\/3397230.3397238"},{"key":"1008_CR36","doi-asserted-by":"publisher","unstructured":"Zhu, R., Wu, Z., Han, Y., et al. (2021). Flat: Fast, lightweight and accurate method for cardinality estimation. Proceedings VLDB Endowment,14(9), 1489\u20131502. https:\/\/doi.org\/10.14778\/3461535.3461539","DOI":"10.14778\/3461535.3461539"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01008-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-025-01008-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01008-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T02:46:15Z","timestamp":1778035575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-025-01008-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,21]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1008"],"URL":"https:\/\/doi.org\/10.1007\/s10844-025-01008-5","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,21]]},"assertion":[{"value":"16 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}