{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:10:15Z","timestamp":1780423815072,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":41,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFA0709400"],"award-info":[{"award-number":["2019YFA0709400"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education AcRF Tier 2 grant, Singapore","award":["MOE-T2EP20121-0016"],"award-info":[{"award-number":["MOE-T2EP20121-0016"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100004000","name":"Guangzhou Science and Technology Program key projects","doi-asserted-by":"publisher","award":["2023A03J0143,2024A04J4458"],"award-info":[{"award-number":["2023A03J0143,2024A04J4458"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306256"],"award-info":[{"award-number":["62306256"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709271","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"1669-1678","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["ScalaGBM: Memory Efficient GBDT Training for High-Dimensional Data on GPU"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8226-4661","authenticated-orcid":false,"given":"Borui","family":"Xu","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-6053","authenticated-orcid":false,"given":"Zeyi","family":"Wen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China & Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5798-2282","authenticated-orcid":false,"given":"Yao","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8834-0453","authenticated-orcid":false,"given":"Weiguo","family":"Liu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, Shandong Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-2053","authenticated-orcid":false,"given":"Weng-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8618-4581","authenticated-orcid":false,"given":"Bingsheng","family":"He","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Yggdrasil: An optimized system for training deep decision trees at scale. Advances in Neural Information Processing Systems 29","author":"Abuzaid Firas","year":"2016","unstructured":"Firas Abuzaid, Joseph K Bradley, Feynman T Liang, Andrew Feng, Lee Yang, Matei Zaharia, and Ameet S Talwalkar. 2016. Yggdrasil: An optimized system for training deep decision trees at scale. Advances in Neural Information Processing Systems 29 (2016)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_4_1","unstructured":"ML Contests. 2023. Tabular Data Competitions - Winning Strategies. https:\/\/mlcontests.com\/tabular-data\/"},{"key":"e_1_3_2_2_5_1","volume-title":"Practical machine learning with H2O: powerful, scalable techniques for deep learning and AI. '' O'Reilly Media","author":"Cook Darren","unstructured":"Darren Cook. 2016. Practical machine learning with H2O: powerful, scalable techniques for deep learning and AI. '' O'Reilly Media, Inc.''."},{"key":"e_1_3_2_2_6_1","unstructured":"David L Donoho et al. 2000. High-dimensional data analysis: The curses and blessings of dimensionality. AMS math challenges lecture 1 2000 (2000) 32."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/3329772.3329780"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342273"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236212"},{"key":"e_1_3_2_2_10_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Gorishniy Yury","year":"2021","unstructured":"Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revisiting Deep Learning Models for Tabular Data. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 18932--18943. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/9d86d83f925f2149e9edb0ac3b49229c-Paper.pdf"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375670"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/hhaa009"},{"key":"e_1_3_2_2_13_1","first-page":"25422","article-title":"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems","volume":"35","author":"Iosipoi Leonid","year":"2022","unstructured":"Leonid Iosipoi and Anton Vakhrushev. 2022. SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems. Advances in Neural Information Processing Systems 35 (2022), 25422--25435. https:\/\/openreview.net\/forum?id=WSxarC8t-T","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196892"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2017.87"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_2_17_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 3149--3157."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330858"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330676"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/628"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157239"},{"key":"e_1_3_2_2_22_1","first-page":"1","article-title":"MLlib: Machine Learning in Apache Spark","volume":"17","author":"Meng Xiangrui","year":"2016","unstructured":"Xiangrui Meng, Joseph Bradley, Burak Yavuz, Evan Sparks, Shivaram Venkataraman, Davies Liu, Jeremy Freeman, DB Tsai, Manish Amde, Sean Owen, Doris Xin, Reynold Xin, Michael J. Franklin, Reza Zadeh, Matei Zaharia, and Ameet Talwalkar. 2016. MLlib: Machine Learning in Apache Spark. Journal of Machine Learning Research 17, 34 (2016), 1--7. http:\/\/jmlr.org\/papers\/v17\/15--237.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.127"},{"key":"e_1_3_2_2_24_1","unstructured":"Paul Mooney. 2022. Kaggle Survey 2022: All Results. https:\/\/www.kaggle.com\/code\/paultimothymooney\/kaggle-survey-2022-all-results\/notebook"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","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. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (Montr\u00e9al, Canada) (NIPS'18). Curran Associates Inc., Red Hook, NY, USA, 6639--6649."},{"key":"e_1_3_2_2_27_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ut1vF_q_vC","author":"Qin Zhen","year":"2021","unstructured":"Zhen Qin, Le Yan, Honglei Zhuang, Yi Tay, Rama Kumar Pasumarthi, Xuanhui Wang, Michael Bendersky, and Marc Najork. 2021. Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees?. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ut1vF_q_vC"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13042749"},{"key":"e_1_3_2_2_29_1","volume-title":"Oh (Eds.)","volume":"35","author":"Shi Yu","year":"2022","unstructured":"Yu Shi, Guolin Ke, Zhuoming Chen, Shuxin Zheng, and Tie-Yan Liu. 2022. Quantized Training of Gradient Boosting Decision Trees. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 18822--18833. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/77911ed9e6e864ca1a3d165b2c3cb258-Paper-Conference.pdf"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.01.014"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3485450.3485459"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.frl.2018.12.032"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.14778\/3494124.3494126"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137867"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00033"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/632"},{"key":"e_1_3_2_2_38_1","first-page":"1","article-title":"ThunderGBM: Fast GBDTs and Random Forests on GPUs","volume":"21","author":"Wen Zeyi","year":"2020","unstructured":"Zeyi Wen, Hanfeng Liu, Jiashuai Shi, Qinbin Li, Bingsheng He, and Jian Chen. 2020. ThunderGBM: Fast GBDTs and Random Forests on GPUs. Journal of Machine Learning Research 21, 108 (2020), 1--5. http:\/\/jmlr.org\/papers\/v21\/19-095.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2920131"},{"key":"e_1_3_2_2_40_1","volume-title":"JMLR Workshop and Conference Proceedings. To appear.","author":"Yu Hsiang-Fu","year":"2011","unstructured":"Hsiang-Fu Yu, Hung-Yi Lo, Hsun-Ping Hsieh, Jing-Kai Lou, Todd G. McKenzie, Jung-Wei Chou, Po-Han Chung, Chia-Hua Ho, Chun-Fu Chang, Yin-Hsuan Wei, Jui-Yu Weng, En-Syu Yan, Che-Wei Chang, Tsung-Ting Kuo, Yi-Chen Lo, Po Tzu Chang, Chieh Po, Chien-Yuan Wang, Yi-Hung Huang, Chen-Wei Hung, Yu-Xun Ruan, Yu-Shi Lin, Shou-De Lin, Hsuan-Tien Lin, and Chih-Jen Lin. 2011. Feature Engineering and Classifier Ensemble for KDD Cup 2010. In JMLR Workshop and Conference Proceedings. To appear."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3098306"}],"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\/3690624.3709271","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:37:29Z","timestamp":1755358649000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709271"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":41,"alternative-id":["10.1145\/3690624.3709271","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709271","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"}}]}}