{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T07:00:32Z","timestamp":1780642832344,"version":"3.54.1"},"reference-count":217,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tnnls.2022.3229161","type":"journal-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T18:35:29Z","timestamp":1671820529000},"page":"7499-7519","source":"Crossref","is-referenced-by-count":639,"title":["Deep Neural Networks and Tabular Data: A Survey"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4889-9989","authenticated-orcid":false,"given":"Vadim","family":"Borisov","sequence":"first","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9333-228X","authenticated-orcid":false,"given":"Tobias","family":"Leemann","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3380-4641","authenticated-orcid":false,"given":"Kathrin","family":"Se\u00dfler","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1286-3551","authenticated-orcid":false,"given":"Johannes","family":"Haug","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6191-4434","authenticated-orcid":false,"given":"Martin","family":"Pawelczyk","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3123-7268","authenticated-orcid":false,"given":"Gjergji","family":"Kasneci","sequence":"additional","affiliation":[{"name":"Data Science and Analytics Research (DSAR) Group, University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1404.7828"},{"key":"ref2","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref7","article-title":"Neural oblivious decision ensembles for deep learning on tabular data","author":"Popov","year":"2019","journal-title":"arXiv:1909.06312"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"ref9","article-title":"SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training","author":"Somepalli","year":"2021","journal-title":"arXiv:2106.01342"},{"key":"ref10","first-page":"1","article-title":"Well-tuned simple nets excel on tabular datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kadra"},{"key":"ref11","first-page":"341","article-title":"Trust Issues: Uncertainty estimation does not enable reliable OOD detection on medical tabular data","volume-title":"Proc. Mach. Learn. Health NeurIPS Workshop","author":"Ulmer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/euaa377"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbr.2021.100116"},{"key":"ref14","article-title":"Sequential deep learning for credit risk monitoring with tabular financial data","author":"Clements","year":"2020","journal-title":"arXiv:2012.15330"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"issue":"1","key":"ref16","first-page":"1","article-title":"Deep learning based recommender system: A survey and new perspectives","volume":"52","author":"Shuai","year":"2017","journal-title":"ACM Comput. Surv."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3069058"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1142\/S2424922X17500073"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2494502"},{"key":"ref20","first-page":"1","article-title":"Adversarial attacks for tabular data: Application to fraud detection and imbalanced data","volume-title":"Proc. CEUR Workshop","volume":"2808","author":"Cartella"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/met0000374"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3162123"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3184723"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116269"},{"key":"ref25","article-title":"Online deep learning: Learning deep neural networks on the fly","author":"Sahoo","year":"2017","journal-title":"arXiv:1711.03705"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref28","article-title":"Generative adversarial networks in computer vision: A survey and taxonomy","author":"Wang","year":"2019","journal-title":"arXiv:1906.01529"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.03.083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","article-title":"New properties of the data distillation method when working with tabular data","author":"Medvedev","year":"2020","journal-title":"arXiv:2010.09839"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/e22111203"},{"key":"ref33","article-title":"IFedAvg: Interpretable data-interoperability for federated learning","author":"Roschewitz","year":"2021","journal-title":"arXiv:2107.06580"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04013-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3136385"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114582"},{"key":"ref37","article-title":"Synthesising multi-modal minority samples for tabular data","volume-title":"arXiv:2105.08204","author":"Darabi","year":"2021"},{"key":"ref38","article-title":"Copula flows for synthetic data generation","author":"Kamthe","year":"2021","journal-title":"arXiv:2101.00598"},{"key":"ref39","first-page":"286","article-title":"Generating multi-label discrete patient records using generative adversarial networks","volume-title":"Proc. 2nd Mach. Learn. Healthcare Conf.","author":"Choi"},{"key":"ref40","volume-title":"California Consumer Privacy Act (CCPA)","year":"2018"},{"key":"ref41","volume-title":"Regulation (EU) 2016\/679 of the European Parliament and of the Council","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57959-7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3116481"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.01.052"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3375624"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00305-w"},{"key":"ref48","article-title":"Revisiting deep learning models for tabular data","author":"Gorishniy","year":"2021","journal-title":"arXiv:2106.11959"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","first-page":"1","article-title":"Net-DNF: Effective deep modeling of tabular data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Katzir"},{"key":"ref51","volume-title":"Introduction to Statistics","author":"David","year":"2003"},{"key":"ref52","volume-title":"Deep Learning With Structured Data","author":"Ryan","year":"2020"},{"key":"ref53","article-title":"Deep learning in unconventional domains","author":"Cvitkovic","year":"2020"},{"key":"ref54","volume-title":"UCI Machine Learning Repository","author":"Dua","year":"2017"},{"issue":"1","key":"ref55","first-page":"293","article-title":"The sunstroke epidemic of Cincinnati, Ohio, during the summer of 1881","volume-title":"Public Health Papers Rep.","volume":"7","author":"Miles","year":"1881"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref57","article-title":"Human mortality database","volume-title":"Encyclopedia Gerontology Population Aging","author":"Jdanov","year":"2020"},{"key":"ref58","author":"Fix","year":"1951","journal-title":"Discriminatory Analysis: Nonparametric Discrimination, Consistency Properties"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.3.393"},{"key":"ref60","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-4028-0","volume-title":"Statistical Disclosure Control in Practice","volume":"111","author":"Willenborg","year":"1996"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330858"},{"key":"ref63","first-page":"1379","article-title":"Regularization learning networks: Deep learning for tabular datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shavitt"},{"key":"ref64","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref65","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref66","article-title":"Transformers in vision: A survey","author":"Khan","year":"2021","journal-title":"arXiv:2101.01169"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.stamet.2005.08.005"},{"key":"ref69","article-title":"Synthesizing tabular data using generative adversarial networks","author":"Xu","year":"2018","journal-title":"arXiv:1811.11264"},{"key":"ref70","first-page":"3146","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ke"},{"key":"ref71","first-page":"6638","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Prokhorenkova"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90923-y"},{"key":"ref73","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman"},{"key":"ref74","article-title":"The spatial inductive bias of deep learning","author":"Mitchell","year":"2017"},{"key":"ref75","article-title":"On embeddings for numerical features in tabular deep learning","author":"Gorishniy","year":"2022","journal-title":"arXiv:2203.05556"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32909-8_35"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00360"},{"key":"ref79","first-page":"1","article-title":"VIME: Extending the success of self- and semi-supervised learning to tabular domaindim","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yoon"},{"key":"ref80","article-title":"SCARF: Self-supervised contrastive learning using random feature corruption","author":"Bahri","year":"2021","journal-title":"arXiv:2106.15147"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"ref82","article-title":"Distilling a neural network into a soft decision tree","author":"Frosst","year":"2017","journal-title":"arXiv:1711.09784"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"ref84","volume-title":"TabNN: A Universal Neural Network Solution for Tabular Data","author":"Ke","year":"2018"},{"key":"ref85","article-title":"Neural additive models: Interpretable machine learning with neural nets","author":"Agarwal","year":"2020","journal-title":"arXiv:2004.13912"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401437"},{"key":"ref87","article-title":"DNN2LR: Interpretation-inspired feature crossing for real-world tabular data","author":"Liu","year":"2020","journal-title":"arXiv:2008.09775"},{"key":"ref88","first-page":"1","article-title":"Boost then Convolve: Gradient boosting meets graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ivanov"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3070575"},{"key":"ref90","article-title":"TabTransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020","journal-title":"arXiv:2012.06678"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457321"},{"key":"ref92","first-page":"28742","article-title":"Self-attention between datapoints: Going beyond individual input-output pairs in deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kossen"},{"key":"ref93","first-page":"8952","article-title":"Feature selection using stochastic gates","volume-title":"Proc. Mach. Learn. Syst.","author":"Yamada"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/507533.507538"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9473(01)00065-2"},{"key":"ref96","first-page":"113","article-title":"Oblivious decision trees and abstract cases","volume-title":"Proc. Work. Notes AAAI Workshop Case-Based Reasoning","author":"Langley"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1146"},{"key":"ref98","volume-title":"MNIST Handwritten Digit Database","author":"LeCun","year":"2010"},{"key":"ref99","article-title":"Entity embeddings of categorical variables","author":"Guo","year":"2016","journal-title":"arXiv:1604.06737"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref101","first-page":"985","article-title":"Fast discriminative visual codebooks using randomized clustering forests","volume-title":"Proc. 20th Annu. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Moosmann"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref104","article-title":"Language models with transformers","author":"Wang","year":"2019","journal-title":"arXiv:1904.09408"},{"key":"ref105","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","author":"Martins","year":"2016","journal-title":"arXiv:1602.02068"},{"key":"ref106","author":"Van Rossum","year":"1995","journal-title":"Python Reference Manual"},{"key":"ref107","article-title":"PyTorch tabular: A framework for deep learning with tabular data","author":"Joseph","year":"2021","journal-title":"arXiv:2104.13638"},{"key":"ref108","article-title":"Fairness in TabNet model by disentangled representation for the prediction of hospital no-show","author":"Boughorbel","year":"2021","journal-title":"arXiv:2103.04048"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30484-3_6"},{"key":"ref113","article-title":"Lockout: Sparse regularization of neural networks","author":"Valdes","year":"2021","journal-title":"arXiv:2107.07160"},{"key":"ref114","article-title":"Simple modifications to improve tabular neural networks","author":"Fiedler","year":"2021","journal-title":"arXiv:2108.03214"},{"key":"ref115","article-title":"Muddling label regularization: Deep learning for tabular datasets","author":"Lounici","year":"2021","journal-title":"arXiv:2106.04462"},{"key":"ref116","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. NeurIPS","author":"Lundberg"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/287"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_21"},{"key":"ref119","first-page":"1","article-title":"Working with deep generative models and tabular data imputation","volume-title":"Proc. ICML Artemiss Workshop","author":"Camino"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3361016"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa127"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407802"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref124","first-page":"1","article-title":"Adversarial ranking for language generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2629"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA.2016.49"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW51313.2020.00082"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3134428"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1968.1054142"},{"key":"ref130","first-page":"1","article-title":"Modeling tabular data using conditional GAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xu"},{"key":"ref131","first-page":"1","article-title":"Generating privacy-preserving synthetic tabular data using oblivious variational autoencoders","volume-title":"Proc. Workshop Econ. Privacy Data Labor 37th Int. Conf. Mach. Learn.","author":"Vardhan"},{"key":"ref132","first-page":"4747","article-title":"Synthsonic: Fast, probabilistic modeling and synthesis of tabular data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Baak"},{"key":"ref133","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014","journal-title":"arXiv:1406.2661"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1511.06434"},{"key":"ref135","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref136","first-page":"5769","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref137","article-title":"The Cram\u00e9r distance as a solution to biased Wasserstein gradients","author":"Bellemare","year":"2017","journal-title":"arXiv:1705.10743"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.08431"},{"key":"ref139","first-page":"3310","article-title":"VEEGAN: Reducing mode collapse in GANs using implicit variational learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref140","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent. (ICLR), Conf. Track","author":"Kingma"},{"key":"ref141","first-page":"1","article-title":"VAEM: A deep generative model for heterogeneous mixed type data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ma"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231757"},{"key":"ref143","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref144","article-title":"Causal-TGAN: Generating tabular data using causal generative adversarial networks","author":"Wen","year":"2021","journal-title":"arXiv:2104.10680"},{"key":"ref145","first-page":"1","article-title":"PATE-GAN: Generating synthetic data with differential privacy guarantees","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jordon"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3212627"},{"key":"ref147","article-title":"Airline passenger name record generation using generative adversarial networks","author":"Mottini","year":"2018","journal-title":"arXiv:1807.06657"},{"key":"ref148","first-page":"1","article-title":"Generating multi-categorical samples with generative adversarial networks","volume-title":"Proc. ICML Workshop Theor. Found. Appl. Deep Generative Models","author":"Camino"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy142"},{"key":"ref150","article-title":"CTAB-GAN: Effective table data synthesizing","author":"Zhao","year":"2021","journal-title":"arXiv:2102.08369"},{"key":"ref151","article-title":"Language models are realistic tabular data generators","author":"Borisov","year":"2022","journal-title":"arXiv:2210.06280"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1951.10500769"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3027314"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185901"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3332281"},{"key":"ref157","first-page":"1","article-title":"CARLA: A Python library to benchmark algorithmic recourse and counterfactual explanation algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS) Benchmark Datasets Track","author":"Pawelczyk"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339556"},{"key":"ref159","first-page":"1","article-title":"Towards robust interpretability with self-explaining neural networks","volume-title":"Proc. NeurIPS","author":"Alvarez-Melis"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300831"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_10"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983746"},{"key":"ref164","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"ref169","article-title":"On baselines for local feature attributions","author":"Haug","year":"2021","journal-title":"arXiv:2101.00905"},{"key":"ref170","first-page":"1","article-title":"Synthetic benchmarks for scientific research in explainable machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS) Benchmark Datasets Track","author":"Liu"},{"issue":"2","key":"ref171","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2018","journal-title":"Harvard J. Law Technol."},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287566"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287569"},{"key":"ref174","first-page":"12187","article-title":"Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses","volume-title":"Proc. NeurIPS","author":"Rawal"},{"key":"ref175","first-page":"895","article-title":"Model-agnostic counterfactual explanations for consequential decisions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Karimi"},{"key":"ref176","first-page":"1","article-title":"Explanations based on the missing: Towards contrastive explanations with pertinent negatives","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dhurandhar"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287574"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380087"},{"key":"ref179","first-page":"1","article-title":"CRUDS: Counterfactual recourse using disentangled subspaces","volume-title":"Proc. ICML Workshop Hum. Interpretability Mach. Learn. (WHI)","author":"Downs"},{"key":"ref180","article-title":"Towards realistic individual recourse and actionable explanations in black-box decision making systems","author":"Joshi","year":"2019","journal-title":"arXiv:1907.09615"},{"key":"ref181","article-title":"Preserving causal constraints in counterfactual explanations for machine learning classifiers","author":"Mahajan","year":"2019","journal-title":"arXiv:1912.03277"},{"key":"ref182","first-page":"809","article-title":"On counterfactual explanations under predictive multiplicity","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Pawelczyk"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107501"},{"key":"ref184","first-page":"16926","article-title":"Towards robust and reliable algorithmic recourse","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Upadhyay"},{"key":"ref185","first-page":"5324","article-title":"On the adversarial robustness of causal algorithmic recourse","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Dominguez-Olmedo"},{"key":"ref186","article-title":"Probabilistically robust recourse: Navigating the trade-offs between costs and robustness in algorithmic recourse","author":"Pawelczyk","year":"2022","journal-title":"arXiv:2203.06768"},{"key":"ref187","article-title":"A survey of algorithmic recourse: Definitions, formulations, solutions, and prospects","author":"Karimi","year":"2020","journal-title":"arXiv:2010.04050"},{"key":"ref188","article-title":"Counterfactual explanations for machine learning: A review","author":"Verma","year":"2020","journal-title":"arXiv:2010.10596"},{"key":"ref189","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref191","volume-title":"Home Equity Line of Credit (HELOC) Dataset","year":"2019"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5308"},{"key":"ref193","doi-asserted-by":"crossref","DOI":"10.4135\/9781412985116","volume-title":"Monte Carlo Simulation","author":"Mooney","year":"1997"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-7152(96)00140-X"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/281"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"issue":"239","key":"ref200","first-page":"2","article-title":"Docker: Lightweight Linux containers for consistent development and deployment","volume":"2014","author":"Merkel","year":"2014","journal-title":"Linux J."},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2020.07.007"},{"key":"ref202","first-page":"18770","article-title":"A consistent and efficient evaluation strategy for attribution methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rong"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6064"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1356"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3172365"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2775225"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347107"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220005"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.2478\/jaiscr-2020-0002"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403200"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412499"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref217","first-page":"1","article-title":"SubTab: Subsetting features of tabular data for self-supervised representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ucar"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10547160\/09998482.pdf?arnumber=9998482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T05:35:22Z","timestamp":1725341722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9998482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":217,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3229161","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}