{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:42:48Z","timestamp":1765392168163,"version":"3.46.0"},"reference-count":68,"publisher":"Tsinghua University Press","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376073"],"award-info":[{"award-number":["62376073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong","doi-asserted-by":"publisher","award":["2024A1515030024"],"award-info":[{"award-number":["2024A1515030024"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Big Data Min. Anal."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.26599\/bdma.2025.9020055","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T18:35:44Z","timestamp":1765305344000},"page":"263-283","source":"Crossref","is-referenced-by-count":0,"title":["Interpret When Possible: A Tree-Based Hybrid Framework for Interpretable Classification"],"prefix":"10.26599","volume":"9","author":[{"given":"Yifan","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhan","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Xing","sequence":"additional","affiliation":[{"name":"Shenzhen Zhice Technology Co., Ltd.,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology,Shenzhen,China,518000"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref2","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3247480"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3308446"},{"volume-title":"Interpretable Machine Learning","year":"2020","author":"Molnar","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3584371.3613002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2021.101539"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/388"},{"key":"ref12","first-page":"9525","article-title":"Sanity checks for saliency maps","volume-title":"Proc. 32nd Int. Conf. Neural Information Processing Systems","author":"Adebayo"},{"key":"ref13","first-page":"4794","article-title":"Framework forevaluating faithfulness of local explanations","volume-title":"Proc. 39th Int. Conf. Machine Learning, Baltimore, MD, USA","author":"Dasgupta","year":"2022"},{"key":"ref14","first-page":"1855","article-title":"Optimization methods for interpretable differentiable decision trees applied to reinforcement learning","volume-title":"Proc. 23rd Int. Conf. Artificial Intelligence and Statistics","author":"Silva"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3328881"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3359786"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref19","first-page":"6505","article-title":"Gaining free or low-cost interpretability with interpretable partial substitute","volume-title":"Proc. 36th Int. Conf. Machine Learning","author":"Wang"},{"issue":"1","key":"ref20","first-page":"137","article-title":"Hybrid predictive models: When an interpretable model collaborates with a black-box model","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"732","article-title":"Transparency promotion with model-agnostic linear competitors","volume-title":"Proc. 37th Int. Conf. Machine Learning","author":"Rafique","year":"2020"},{"key":"ref22","first-page":"2444","article-title":"Interpretable companions for black-box models","volume-title":"Proc. 23rd Int. Conf. Artificial Intelligence and Statistics","author":"Pan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1900654116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/2530946"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7070-7_8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOAS848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3225162"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20551"},{"key":"ref30","first-page":"495","article-title":"Concept bottleneck models","volume-title":"Proc. 37th Int. Conf. Machine Learning","author":"Koh","year":"2020"},{"key":"ref31","first-page":"1","article-title":"Label-free concept bottleneck models","volume-title":"Proc. 11th Int. Conf. Learning Representations","author":"Oikarinen"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110599"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref35","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. 31st Int. Conf. Neural Information Processing Systems","author":"Lundberg"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475337"},{"key":"ref37","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. 2nd Int. Conf. Learning Representations","author":"Simonyan","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372850"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00831-6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379251"},{"issue":"1","key":"ref42","first-page":"264","article-title":"ProtoryNet-interpretable text classification via prototype trajectories","volume":"24","author":"Hong","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","first-page":"719","article-title":"Reliable post hoc explanations: Modeling uncertainty in explainability","volume-title":"Proc. 35th Int. Conf. Neural Information Processing Systems","author":"Slack","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21452"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313119"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/376"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2004.843247"},{"volume-title":"C4. 5: Programs for Machine Learning","year":"1993","author":"Quinlan","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470"},{"key":"ref50","article-title":"Distilling a neural network into a soft decision tree","author":"Frosst","year":"2017","journal-title":"arXiv preprint"},{"key":"ref51","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Machine Learning","volume":"48","author":"Martins"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50035-8"},{"key":"ref53","first-page":"1","article-title":"Decision boundary analysis of adversarial examples","volume-title":"Proc. 6th Int. Conf. Learning Representations","author":"He"},{"key":"ref54","first-page":"1122","article-title":"Robust decision trees against adversarial examples","volume-title":"Proc. 36th Int. Conf. Machine Learning","author":"Chen"},{"key":"ref55","first-page":"37","article-title":"Why do tree-based models still outperform deep learning on typical tabular data","volume-title":"Proc. 36th Int. Conf. Neural Information Processing Systems","author":"Grinsztajn"},{"volume-title":"Logistic Regression","year":"2002","author":"Kleinbaum","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"volume-title":"Neural Networks: A Comprehensive Foundation","year":"1998","author":"Haykin","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"ref61","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. 35th Int. Conf. Machine Learning","author":"Kim"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01865"},{"key":"ref63","article-title":"Prior-fitted networks scale to larger datasets when treated as weak learners","author":"Wang","year":"2025","journal-title":"arXiv preptint"},{"key":"ref64","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. 31st Int. Conf. Neural Information Processing Systems","author":"Ke"},{"key":"ref65","first-page":"6639","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. 32nd Int. Conf. Neural Information Processing Systems","author":"Prokhorenkova"},{"key":"ref66","first-page":"1","article-title":"SAINT: Improved neural networks for tabular data via row attention and contrastive pretraining","volume-title":"Proc. NeurIPS 2022 First Table Representation Workshop","author":"Somepalli"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671893"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889204"}],"container-title":["Big Data Mining and Analytics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8254253\/11293067\/11293109.pdf?arnumber=11293109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T18:34:56Z","timestamp":1765391696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11293109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":68,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.26599\/bdma.2025.9020055","relation":{},"ISSN":["2096-0654","2097-406X"],"issn-type":[{"type":"print","value":"2096-0654"},{"type":"electronic","value":"2097-406X"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}