{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T13:23:21Z","timestamp":1783949001115,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Understanding Implicit Dataset Relationships for Machine Learning","award":["VI.Veni.222.439"],"award-info":[{"award-number":["VI.Veni.222.439"]}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union Horizon Programme","award":["101093164"],"award-info":[{"award-number":["101093164"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tkde.2024.3357389","type":"journal-article","created":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T20:51:52Z","timestamp":1706043112000},"page":"7353-7367","source":"Crossref","is-referenced-by-count":14,"title":["Amalur: The Convergence of Data Integration and Machine Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9403-572X","authenticated-orcid":false,"given":"Ziyu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7849-7771","authenticated-orcid":false,"given":"Wenbo","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danning","family":"Zhan","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Kang","sequence":"additional","affiliation":[{"name":"WeBank, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lydia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Neuchatel, Neuchâtel, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3300-2913","authenticated-orcid":false,"given":"Alessandro","family":"Bozzon","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3720-6585","authenticated-orcid":false,"given":"Rihan","family":"Hai","sequence":"additional","affiliation":[{"name":"Department of Software Technology, Delft University of Technology, Delft, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0201645"},{"key":"ref2","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/c2011-0-06130-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s007780100057"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02463-4_12"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.58729\/1941-6687.1324"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2958084"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2994641"},{"key":"ref9","first-page":"423","article-title":"Learning models over relational data: A brief tutorial","volume-title":"Proc. Int. Conf. Scalable Uncertainty Manage.","author":"Maximilian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3388870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389742"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920904"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035960"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00171"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.14778\/2994509.2994514"},{"key":"ref16","article-title":"BoostClean: Automated error detection and repair for machine learning","author":"Krishnan","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3197387"},{"key":"ref19","first-page":"9","article-title":"Data integration: The teenage years","volume-title":"Proc. 32nd Int. Conf. Very Large Data Bases","author":"Halevy"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2200\/s00960ed2v01y201910aim043"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62328-8"},{"key":"ref22","article-title":"Summary of the HIPAA privacy rule - hhs.gov"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/543613.543644"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3034786.3056124"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.14778\/3282495.3282499"},{"key":"ref28","first-page":"147","article-title":"Willump: A statistically-aware end-to-end optimizer for machine learning inference","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","author":"Kraft"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1634.1636"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_64189"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397235"},{"key":"ref32","first-page":"331","article-title":"COCOA: Correlation coefficient-aware data augmentation","volume-title":"Proc. 24th Int. Conf. Extending Database Technol.","author":"Esmailoghli"},{"key":"ref33","first-page":"19","article-title":"To join or not to join? Thinking twice about joins before feature selection","volume-title":"Proc. ACM SIGMOD Int. Conf. Manage. Data","author":"Kumar"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882939"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137633"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457311"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2899389"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34444-2_31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.7250\/csimq.2016-9.04"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1247480.1247553"},{"key":"ref43","first-page":"209","article-title":"Applying model management to classical meta data problems","volume-title":"Proc. Int. Conf. Innov. Data Syst. Res.","author":"Bernstein"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1065167.1065176"},{"key":"ref45","article-title":"Database system concepts","author":"Silberschatz","year":"2011"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/1048935.1050184"},{"issue":"3","key":"ref47","first-page":"5","article-title":"Managing Google\u2019s data lake: An overview of the Goods system","volume":"39","author":"Halevy","year":"2016","journal-title":"IEEE Data Eng. Bull."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00047"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457403"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3555041.3589732"},{"key":"ref52","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yosinski"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"ref54","article-title":"Transfer learning with deep tabular models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Levin"},{"key":"ref55","article-title":"STable: Table generation framework for encoder-decoder models","volume-title":"Proc. NeurIPS 1st Table Representation Workshop","author":"Micha\u0142"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.14778\/3565816.3565831"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610527"},{"issue":"101","key":"ref58","article-title":"DAWNBench: An end-to-end deep learning benchmark and competition","volume":"100","author":"Coleman","year":"2017","journal-title":"Training"},{"key":"ref59","article-title":"XLA: Compiling machine learning for peak performance","author":"Sabne","year":"2020"},{"key":"ref60","article-title":"Efficient inference with tensorrt","volume-title":"Proc. GPU Technol. Conf.","author":"Vanholder"},{"key":"ref61","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551833"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517869"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661842"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.14778\/3467861.3467869"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICDEW58674.2023.00034"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3209889.3209896"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476372"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319878"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00103"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533044"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE51399.2021.00103"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3369554"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2013.01.002"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3418896"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref78","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Conf. Operating Syst. Des. Implementation","author":"Chen"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322967"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2021.3082561"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526127"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457241"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482361"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/BigDIA56350.2022.9874186"},{"key":"ref85","article-title":"SplitFed: When federated learning meets split learning","author":"Thapa","year":"2020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1186\/1687-417X-2007-013801"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48910-X_16"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/359168.359176"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20901-7_2"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79228-4_1"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10750897\/10412203.pdf?arnumber=10412203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:24:16Z","timestamp":1732735456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10412203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":89,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3357389","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}