{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T22:38:11Z","timestamp":1783550291044,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SCH-2205289, SCH-2014438, IIS-2034479"],"award-info":[{"award-number":["SCH-2205289, SCH-2014438, IIS-2034479"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671893","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"288-296","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Can a Deep Learning Model be a\n            <i>Sure Bet<\/i>\n            for Tabular Prediction?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3199-2597","authenticated-orcid":false,"given":"Jintai","family":"Chen","sequence":"first","affiliation":[{"name":"Univ. of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2002-2579","authenticated-orcid":false,"given":"Jiahuan","family":"Yan","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0701-8784","authenticated-orcid":false,"given":"Qiyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6565-2884","authenticated-orcid":false,"given":"Danny Z.","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3230-6392","authenticated-orcid":false,"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1512-6426","authenticated-orcid":false,"given":"Jimeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Univ. of Illinois Urbana-Champaign, Urbana, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"e_1_3_2_2_3_1","volume-title":"Henry Mao, Gary Cottrell, and Julian McAuley.","author":"Bachlechner Thomas","year":"2021","unstructured":"Thomas Bachlechner, Bodhisattwa Prasad Majumder, Henry Mao, Gary Cottrell, and Julian McAuley. 2021. Rezero is all you need: Fast convergence at large depth. In Uncertainty in Artificial Intelligence."},{"key":"e_1_3_2_2_4_1","volume-title":"Bagging predictors. Machine Learning","author":"Breiman Leo","year":"1996","unstructured":"Leo Breiman. 1996. Bagging predictors. Machine Learning (1996)."},{"key":"e_1_3_2_2_5_1","volume-title":"TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing. In International Conference on Learning Representations.","author":"Chen Jintai","year":"2023","unstructured":"Jintai Chen, Kuanlun Liao, Yanwen Fang, Danny Z Chen, and Jian Wu. 2023. TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20309"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_2_9_1","volume-title":"International Conference on Artificial Intelligence and Statistics.","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In International Conference on Artificial Intelligence and Statistics."},{"key":"e_1_3_2_2_10_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press."},{"key":"e_1_3_2_2_11_1","unstructured":"Yura Gorishniy Ivan Rubachev and Artem Babenko. 2022. On Embeddings for Numerical Features in Tabular Deep Learning. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_12_1","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."},{"key":"e_1_3_2_2_13_1","unstructured":"Leo Grinsztajn Edouard Oyallon and Gael Varoquaux. 2022. Why do tree-based models still outperform deep learning on typical tabular data?. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467077"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_2_17_1","volume-title":"International Conference on Learning Representations.","author":"Hollmann Noah","year":"2022","unstructured":"Noah Hollmann, Samuel M\u00fcller, Katharina Eggensperger, and Frank Hutter. 2022. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_18_1","volume-title":"TANGOS: Regularizing tabular neural networks through gradient orthogonalization and specialization. arXiv preprint arXiv:2303.05506","author":"Jeffares Alan","year":"2023","unstructured":"Alan Jeffares, Tennison Liu, Jonathan Crabb\u00e9, Fergus Imrie, and Mihaela van der Schaar. 2023. TANGOS: Regularizing tabular neural networks through gradient orthogonalization and specialization. arXiv preprint arXiv:2303.05506 (2023)."},{"key":"e_1_3_2_2_19_1","volume-title":"Well tuned simple nets excel on tabular datasets. Advances in Neural Information Processing Systems","author":"Kadra Arlind","year":"2021","unstructured":"Arlind Kadra, Marius Lindauer, Frank Hutter, and Josif Grabocka. 2021. Well tuned simple nets excel on tabular datasets. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_2_20_1","volume-title":"International Conference on Learning Representations.","author":"Katzir Liran","year":"2020","unstructured":"Liran Katzir, Gal Elidan, and Ran El-Yaniv. 2020. Net-DNF: Effective deep modeling of tabular data. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_21_1","volume-title":"Fahad Shahbaz Khan, and Mubarak Shah.","author":"Khan Salman","year":"2022","unstructured":"Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, and Mubarak Shah. 2022. Transformers in vision: A survey. Comput. Surveys (2022)."},{"key":"e_1_3_2_2_22_1","volume-title":"Can deep learning predict risky retail investors? A case study in financial risk behavior forecasting. European Journal of Operational Research","author":"Kim Alisa","year":"2020","unstructured":"Alisa Kim, Y Yang, Stefan Lessmann, Tiejun Ma, M-C Sung, and Johnnie EV Johnson. 2020. Can deep learning predict risky retail investors? A case study in financial risk behavior forecasting. European Journal of Operational Research (2020)."},{"key":"e_1_3_2_2_23_1","volume-title":"International Conference on Machine Learning.","author":"Kim Jang-Hyun","year":"2020","unstructured":"Jang-Hyun Kim, Wonho Choo, and Hyun Oh Song. 2020. Puzzle Mix: Exploiting saliency and local statistics for optimal mixup. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_24_1","volume-title":"Efficient backprop. Neural networks: Tricks of the Trade","author":"LeCun Yann","year":"2002","unstructured":"Yann LeCun, L\u00e9on Bottou, Genevieve B Orr, and Klaus-Robert M\u00fcller. 2002. Efficient backprop. Neural networks: Tricks of the Trade (2002)."},{"key":"e_1_3_2_2_25_1","volume-title":"Decoupled Weight Decay Regularization. In International Conference on Learning Representations.","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015435"},{"key":"e_1_3_2_2_27_1","volume-title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data. In International Conference on Learning Representations.","author":"Popov Sergei","year":"2019","unstructured":"Sergei Popov, Stanislav Morozov, and Artem Babenko. 2019. Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_28_1","volume-title":"Anna Veronika Dorogush, and Andrey Gulin","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 (2018)."},{"key":"e_1_3_2_2_29_1","volume-title":"Revisiting pretraining objectives for tabular deep learning. arXiv preprint arXiv:2207.03208","author":"Rubachev Ivan","year":"2022","unstructured":"Ivan Rubachev, Artem Alekberov, Yury Gorishniy, and Artem Babenko. 2022. Revisiting pretraining objectives for tabular deep learning. arXiv preprint arXiv:2207.03208 (2022)."},{"key":"e_1_3_2_2_30_1","volume-title":"International Conference on Learning Representations.","author":"Saxe Andrew M","year":"2014","unstructured":"Andrew M Saxe, James L McClelland, and Surya Ganguli. 2014. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_31_1","volume-title":"GLU variants improve Transformer. arXiv preprint arXiv:2002.05202","author":"Shazeer Noam","year":"2020","unstructured":"Noam Shazeer. 2020. GLU variants improve Transformer. arXiv preprint arXiv:2002.05202 (2020)."},{"key":"e_1_3_2_2_32_1","volume-title":"SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342","author":"Somepalli Gowthami","year":"2021","unstructured":"Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C Bayan Bruss, and Tom Goldstein. 2021. SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv preprint arXiv:2106.01342 (2021)."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_2_34_1","volume-title":"Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Medical Image Analysis","author":"Tajbakhsh Nima","year":"2020","unstructured":"Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey N Chiang, Zhihao Wu, and Xiaowei Ding. 2020. Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Medical Image Analysis (2020)."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Machine Learning.","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image Transformers & distillation through attention. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"e_1_3_2_2_37_1","volume-title":"SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization. In International Conference on Learning Representations.","author":"Shahab Uddin AFM","year":"2020","unstructured":"AFM Shahab Uddin, Mst Sirazam Monira, Wheemyung Shin, TaeChoong Chung, and Sung-Ho Bae. 2020. SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_38_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_2_39_1","volume-title":"International Conference on Machine Learning.","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold Mixup: Better representations by interpolating hidden states. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_40_1","volume-title":"Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification. In International Conference on Acoustics, Speech and Signal Processing.","author":"Walawalkar Devesh","year":"2020","unstructured":"Devesh Walawalkar, Zhiqiang Shen, Zechun Liu, and Marios Savvides. 2020. Attentive Cutmix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification. In International Conference on Acoustics, Speech and Signal Processing."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Ruoxi Wang Bin Fu Gang Fu and Mingliang Wang. 2017. Deep & cross network for ad click predictions. In ADKDD.","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_2_43_1","unstructured":"Zifeng Wang and Jimeng Sun. 2022. TransTab: Learning Transferable Tabular Transformers Across Tables. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_2_44_1","volume-title":"Scalable rule-based representation learning for interpretable classification. Advances in Neural Information Processing Systems","author":"Wang Zhuo","year":"2021","unstructured":"Zhuo Wang, Wei Zhang, Ning Liu, and Jianyong Wang. 2021. Scalable rule-based representation learning for interpretable classification. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6102"},{"key":"e_1_3_2_2_46_1","unstructured":"Kevin Wu Eric Wu Michael DAndrea Nandini Chitale Melody Lim Marek Dabrowski Klaudia Kantor Hanoor Rangi Ruishan Liu Marius Garmhausen et al. 2022. Machine learning prediction of clinical trial operational efficiency. The AAPS Journal (2022)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26272"},{"key":"e_1_3_2_2_48_1","unstructured":"Jiahuan Yan Bo Zheng Hongxia Xu Yiheng Zhu Danny Chen Jimeng Sun Jian Wu and Jintai Chen. 2024. Making Pre-trained Language Models Great on Tabular Prediction. In ICLR."},{"key":"e_1_3_2_2_49_1","volume-title":"VIME: Extending the success of self-and semi-supervised learning to tabular domain. Advances in Neural Information Processing Systems","author":"Yoon Jinsung","year":"2020","unstructured":"Jinsung Yoon, Yao Zhang, James Jordon, and Mihaela van der Schaar. 2020. VIME: Extending the success of self-and semi-supervised learning to tabular domain. Advances in Neural Information Processing Systems (2020)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_2_51_1","volume-title":"Mixup: Beyond Empirical Risk Minimization. In International Conference On Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2018. Mixup: Beyond Empirical Risk Minimization. In International Conference On Learning Representations."},{"key":"e_1_3_2_2_52_1","unstructured":"Bingzhao Zhu Xingjian Shi Nick Erickson Mu Li George Karypis and Mahsa Shoaran. 2023. XTab: Cross-table Pretraining for Tabular Transformers. In ICML."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","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 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671893","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671893","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:15Z","timestamp":1750291455000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671893"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":52,"alternative-id":["10.1145\/3637528.3671893","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671893","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}