{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:34:33Z","timestamp":1776440073593,"version":"3.51.2"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031585463","type":"print"},{"value":"9783031585470","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-58547-0_6","type":"book-chapter","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T19:02:10Z","timestamp":1713207730000},"page":"65-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mind the\u00a0Data, Measuring the\u00a0Performance Gap Between Tree Ensembles and\u00a0Deep Learning on\u00a0Tabular Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3089-5525","authenticated-orcid":false,"given":"Axel","family":"Karlsson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0422-6560","authenticated-orcid":false,"given":"Tianze","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7796-5201","authenticated-orcid":false,"given":"Slawomir","family":"Nowaczyk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3272-4145","authenticated-orcid":false,"given":"Sepideh","family":"Pashami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4017-3550","authenticated-orcid":false,"given":"Sahar","family":"Asadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,16]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., Pfister, T.: TabNet: attentive interpretable tabular learning. In: AAAI, vol.\u00a035, pp. 6679\u20136687 (2021)","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"6_CR2","unstructured":"Barr, B., et al.: Towards ground truth explainability on tabular data (2020)"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/S0168-1699(99)00046-0","volume":"24","author":"J Blackard","year":"1999","unstructured":"Blackard, J., Dean, D.: Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Comput. Electron. Agric. 24, 131\u2013151 (1999)","journal-title":"Comput. Electron. Agric."},{"key":"6_CR4","unstructured":"Borisov, V., Leemann, T., Se\u00dfler, K., Haug, J., Pawelczyk, M., Kasneci, G.: Deep neural networks and tabular data: a survey. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD, pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"6_CR6","doi-asserted-by":"publisher","first-page":"74","DOI":"10.2307\/3001634","volume":"9","author":"W Dixon","year":"1953","unstructured":"Dixon, W.: Processing data for outliers. Biometrics 9(1), 74\u201389 (1953)","journal-title":"Biometrics"},{"key":"6_CR7","unstructured":"Dorogush, A.V., Ershov, V., Gulin, A.: CatBoost: gradient boosting with categorical features support. ArXiv abs\/1810.11363 (2018)"},{"key":"6_CR8","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. preprint arXiv:2010.11929 (2020)"},{"key":"6_CR9","first-page":"18932","volume":"34","author":"Y Gorishniy","year":"2021","unstructured":"Gorishniy, Y., Rubachev, I., Khrulkov, V., Babenko, A.: Revisiting deep learning models for tabular data. Adv. Neural. Inf. Process. Syst. 34, 18932\u201318943 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR10","first-page":"507","volume":"35","author":"L Grinsztajn","year":"2022","unstructured":"Grinsztajn, L., Oyallon, E., Varoquaux, G.: Why do tree-based models still outperform deep learning on typical tabular data? Adv. Neural. Inf. Process. Syst. 35, 507\u2013520 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR11","first-page":"23928","volume":"34","author":"A Kadra","year":"2021","unstructured":"Kadra, A., Lindauer, M., Hutter, F., Grabocka, J.: Well-tuned simple nets excel on tabular datasets. NeurIPS 34, 23928\u201323941 (2021)","journal-title":"NeurIPS"},{"key":"6_CR12","unstructured":"Ke, G., et\u00a0al.: LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 3149-3157. NIPS\u201917, Curran Associates Inc. (2017)"},{"key":"6_CR13","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"key":"6_CR14","unstructured":"Levin, R., et\u00a0al.: Transfer learning with deep tabular models. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"6_CR15","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"key":"6_CR16","unstructured":"McElfresh, D., et\u00a0al.: When do neural nets outperform boosted trees on tabular data? (2023)"},{"key":"6_CR17","unstructured":"Miller, C., Hao, L., Fu, C.: Gradient boosting machines and careful pre-processing work best: ASHRAE great energy predictor iii lessons learned (2022)"},{"key":"6_CR18","unstructured":"Mitchell, R., Adinets, A., Rao, T., Frank, E.: XGBoost: scalable GPU accelerated learning. CoRR abs\/1806.11248 (2018)"},{"key":"6_CR19","unstructured":"Radford, A., et\u00a0al.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"6_CR20","first-page":"14501","volume":"35","author":"L Ramp\u00e1\u0161ek","year":"2022","unstructured":"Ramp\u00e1\u0161ek, L., et al.: Recipe for a general, powerful, scalable graph transformer. Adv. Neural. Inf. Process. Syst. 35, 14501\u201314515 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR21","doi-asserted-by":"publisher","first-page":"13233","DOI":"10.1007\/s00521-019-04013-2","volume":"32","author":"A S\u00e1nchez-Morales","year":"2020","unstructured":"S\u00e1nchez-Morales, A., Sancho-G\u00f3mez, J.L., Mart\u00ednez-Garc\u00eda, J.A., Figueiras-Vidal, A.R.: Improving deep learning performance with missing values via deletion and compensation. Neural Comput. Appl. 32, 13233\u201313244 (2020)","journal-title":"Neural Comput. Appl."},{"key":"6_CR22","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","volume":"81","author":"R Shwartz-Ziv","year":"2022","unstructured":"Shwartz-Ziv, R., Armon, A.: Tabular Data: deep learning is not all you need. Inf. Fusion 81, 84\u201390 (2022)","journal-title":"Inf. Fusion"},{"key":"6_CR23","unstructured":"Touvron, H., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"6_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advances in Intelligent Data Analysis XXII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58547-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T19:03:04Z","timestamp":1713207784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58547-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031585463","9783031585470"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58547-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 April 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Intelligent Data Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Stockholm","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ida2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ida2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}