{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T03:40:32Z","timestamp":1759894832278,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3715496","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:12:56Z","timestamp":1748016776000},"page":"1244-1248","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Structural Information in Tree Ensembles for Table Representation Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8729-9456","authenticated-orcid":false,"given":"Nikhil","family":"Pattisapu","sequence":"first","affiliation":[{"name":"Amazon, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1509-4313","authenticated-orcid":false,"given":"Siva Rajesh","family":"Kasa","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4246-2620","authenticated-orcid":false,"given":"Sumegh","family":"Roychowdhury","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5319-327X","authenticated-orcid":false,"given":"Karan","family":"Gupta","sequence":"additional","affiliation":[{"name":"Amazon, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2896-1681","authenticated-orcid":false,"given":"Anish","family":"Bhanushali","sequence":"additional","affiliation":[{"name":"IIIT Bangalore, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4315-9716","authenticated-orcid":false,"given":"Prasanna","family":"Srinivasa Murthy","sequence":"additional","affiliation":[{"name":"Target, Bengaluru, Karnataka, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Openml benchmarking suites. arXiv preprint arXiv:1708.03731","author":"Bischl Bernd","year":"2017","unstructured":"Bernd Bischl, Giuseppe Casalicchio, Matthias Feurer, Pieter Gijsbers, Frank Hutter, Michel Lang, Rafael G Mantovani, Jan N van Rijn, and Joaquin Vanschoren. 2017. Openml benchmarking suites. arXiv preprint arXiv:1708.03731 (2017)."},{"key":"e_1_3_2_1_2_1","volume-title":"Revisiting Multimodal Transformers for Tabular Data with Text Fields. In Findings of the Association for Computational Linguistics ACL","author":"Bonnier Thomas","year":"2024","unstructured":"Thomas Bonnier. 2024. Revisiting Multimodal Transformers for Tabular Data with Text Fields. In Findings of the Association for Computational Linguistics ACL 2024. 1481--1500."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-022-00350-z"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3229161nolinkurl10.1109\/tnnls.2022.3229161"},{"key":"e_1_3_2_1_6_1","unstructured":"Tianqi Chen Tong He Michael Benesty Vadim Khotilovich Yuan Tang Hyunsu Cho Kailong Chen Rory Mitchell Ignacio Cano Tianyi Zhou et al. 2015. Xgboost: extreme gradient boosting. R package version 0.4--2 Vol. 1 4 (2015) 1--4."},{"key":"e_1_3_2_1_7_1","volume-title":"Transfer learning with joint fine-tuning for multimodal sentiment analysis. arXiv preprint arXiv:2210.05790","author":"de Toledo Guilherme Louren\u00e7o","year":"2022","unstructured":"Guilherme Louren\u00e7o de Toledo and Ricardo Marcondes Marcacini. 2022. Transfer learning with joint fine-tuning for multimodal sentiment analysis. arXiv preprint arXiv:2210.05790 (2022)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467228"},{"key":"e_1_3_2_1_9_1","volume-title":"Simple modifications to improve tabular neural networks. arXiv preprint arXiv:2108.03214","author":"Fiedler James","year":"2021","unstructured":"James Fiedler. 2021. Simple modifications to improve tabular neural networks. arXiv preprint arXiv:2108.03214 (2021)."},{"key":"e_1_3_2_1_10_1","unstructured":"Siavash Golkar Mariel Pettee Michael Eickenberg Alberto Bietti Miles Cranmer Geraud Krawezik Francois Lanusse Michael McCabe Ruben Ohana Liam Parker et al. 2023. xval: A continuous number encoding for large language models. arXiv preprint arXiv:2310.02989 (2023)."},{"key":"e_1_3_2_1_11_1","unstructured":"Yury Gorishniy Ivan Rubachev and Artem Babenko. 2022. On Embeddings for Numerical Features in Tabular Deep Learning. In NeurIPS."},{"key":"e_1_3_2_1_12_1","unstructured":"Yury Gorishniy Ivan Rubachev Nikolay Kartashev Daniil Shlenskii Akim Kotelnikov and Artem Babenko. [n. d.]. TabR: Tabular Deep Learning Meets Nearest Neighbors. ( [n. d.])."},{"key":"e_1_3_2_1_13_1","unstructured":"Yury Gorishniy Ivan Rubachev Valentin Khrulkov and Artem Babenko. 2021. Revisiting Deep Learning Models for Tabular Data. In NeurIPS."},{"key":"e_1_3_2_1_14_1","volume-title":"Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems","author":"Grinsztajn L\u00e9o","year":"2022","unstructured":"L\u00e9o Grinsztajn, Edouard Oyallon, and Ga\u00ebl Varoquaux. 2022. Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems, Vol. 35 (2022), 507--520."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.maiworkshop-1.10"},{"key":"e_1_3_2_1_16_1","volume-title":"Tabpfn: A transformer that solves small tabular classification problems in a second. arXiv preprint arXiv:2207.01848","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. arXiv preprint arXiv:2207.01848 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Tabtransformer: Tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678","author":"Huang Xin","year":"2020","unstructured":"Xin Huang, Ashish Khetan, Milan Cvitkovic, and Zohar Karnin. 2020. Tabtransformer: Tabular data modeling using contextual embeddings. arXiv preprint arXiv:2012.06678 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330858"},{"key":"e_1_3_2_1_19_1","volume-title":"Self-normalizing neural networks. Advances in neural information processing systems","author":"Klambauer G\u00fcnter","year":"2017","unstructured":"G\u00fcnter Klambauer, Thomas Unterthiner, Andreas Mayr, and Sepp Hochreiter. 2017. Self-normalizing neural networks. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Tree-Regularized Tabular Embeddings. In NeurIPS 2023 Second Table Representation Learning Workshop. https:\/\/openreview.net\/forum?id=dQLDxIPsU4","author":"Li Xuan","year":"2023","unstructured":"Xuan Li, Yun Wang, and Bo Li. 2023. Tree-Regularized Tabular Embeddings. In NeurIPS 2023 Second Table Representation Learning Workshop. https:\/\/openreview.net\/forum?id=dQLDxIPsU4"},{"key":"e_1_3_2_1_21_1","volume-title":"Interbert: Vision-and-language interaction for multi-modal pretraining. arXiv preprint arXiv:2003.13198","author":"Lin Junyang","year":"2020","unstructured":"Junyang Lin, An Yang, Yichang Zhang, Jie Liu, Jingren Zhou, and Hongxia Yang. 2020. Interbert: Vision-and-language interaction for multi-modal pretraining. arXiv preprint arXiv:2003.13198 (2020)."},{"key":"e_1_3_2_1_22_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_23_1","unstructured":"Duncan McElfresh Sujay Khandagale Jonathan Valverde Vishak Prasad C Benjamin Feuer Chinmay Hegde Ganesh Ramakrishnan Micah Goldblum and Colin White. 2023. When Do Neural Nets Outperform Boosted Trees on Tabular Data?arxiv: 2305.02997 [cs.LG]"},{"key":"e_1_3_2_1_24_1","volume-title":"Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification. arXiv preprint arXiv:2210.07983","author":"Montalvo-Lezama Ricardo","year":"2022","unstructured":"Ricardo Montalvo-Lezama, Berenice Montalvo-Lezama, and Gibran Fuentes-Pineda. 2022. Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification. arXiv preprint arXiv:2210.07983 (2022)."},{"key":"e_1_3_2_1_25_1","volume-title":"Neural oblivious decision ensembles for deep learning on tabular data. arXiv preprint arXiv:1909.06312","author":"Popov Sergei","year":"2019","unstructured":"Sergei Popov, Stanislav Morozov, and Artem Babenko. 2019. Neural oblivious decision ensembles for deep learning on tabular data. arXiv preprint arXiv:1909.06312 (2019)."},{"key":"e_1_3_2_1_26_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, Vol. 31 (2018)."},{"key":"e_1_3_2_1_27_1","volume-title":"Benchmarking multimodal automl for tabular data with text fields. arXiv preprint arXiv:2111.02705","author":"Shi Xingjian","year":"2021","unstructured":"Xingjian Shi, Jonas Mueller, Nick Erickson, Mu Li, and Alexander J Smola. 2021. Benchmarking multimodal automl for tabular data with text fields. arXiv preprint arXiv:2111.02705 (2021)."},{"key":"e_1_3_2_1_28_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_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"e_1_3_2_1_31_1","volume-title":"Making pre-trained language models great on tabular prediction. arXiv preprint arXiv:2403.01841","author":"Yan Jiahuan","year":"2024","unstructured":"Jiahuan Yan, Bo Zheng, Hongxia Xu, Yiheng Zhu, Danny Z Chen, Jimeng Sun, Jian Wu, and Jintai Chen. 2024. Making pre-trained language models great on tabular prediction. arXiv preprint arXiv:2403.01841 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Converting tabular data into images for deep learning with convolutional neural networks. Scientific reports","author":"Zhu Yitan","year":"2021","unstructured":"Yitan Zhu, Thomas Brettin, Fangfang Xia, Alexander Partin, Maulik Shukla, Hyunseung Yoo, Yvonne A Evrard, James H Doroshow, and Rick L Stevens. 2021. Converting tabular data into images for deep learning with convolutional neural networks. Scientific reports, Vol. 11, 1 (2021), 11325."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715496","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3715496","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T03:02:44Z","timestamp":1759892564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3715496"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":32,"alternative-id":["10.1145\/3701716.3715496","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3715496","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}