{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T09:56:20Z","timestamp":1779011780300,"version":"3.51.4"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031706288","type":"print"},{"value":"9783031706264","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70626-4_13","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T03:01:52Z","timestamp":1725159712000},"page":"184-198","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing Machine Learning Capabilities in\u00a0Data Lakes with\u00a0AutoML and\u00a0LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-9025","authenticated-orcid":false,"given":"Sayed","family":"Hoseini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4323-9804","authenticated-orcid":false,"given":"Maximilian","family":"Ibbels","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1698-4345","authenticated-orcid":false,"given":"Christoph","family":"Quix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,1]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6549-9_3","volume-title":"What Is MLOps?","author":"S Alla","year":"2021","unstructured":"Alla, S., Adari, S.K.: What Is MLOps? Apress, Berkeley, CA (2021)"},{"issue":"5","key":"13_CR2","first-page":"4646","volume":"35","author":"C Chai","year":"2023","unstructured":"Chai, C., Wang, J., Luo, Y., Niu, Z., Li, G.: Data management for machine learning: a survey. IEEE TKDE 35(5), 4646\u20134667 (2023)","journal-title":"IEEE TKDE"},{"key":"13_CR3","unstructured":"Chen, A., Dohan, D.M., So, D.R.: Evoprompting: Language models for code-level neural architecture search (2023)"},{"key":"13_CR4","unstructured":"Chen, T., et al.: Dual-awareness attention for few-shot object detection. CoRR abs\/2102.12152 (2021)"},{"key":"13_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-031-15740-0_14","volume-title":"ADBIS","author":"C Diamantini","year":"2022","unstructured":"Diamantini, C., et al.: A knowledge-based approach to support analytic query answering in semantic data lakes. In: Chiusano, S., Cerquitelli, T., Wrembel, R. (eds.) ADBIS. LNCS, vol. 13389, pp. 179\u2013192. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15740-0_14"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Hai, R., et al.: Amalur: data integration meets machine learning. In: 39th IEEE ICDE 2023, Anaheim, CA, USA, April 3-7, 2023, pp. 3729\u20133739. IEEE (2023)","DOI":"10.1109\/ICDE55515.2023.00301"},{"issue":"12","key":"13_CR7","first-page":"12571","volume":"35","author":"R Hai","year":"2023","unstructured":"Hai, R., Koutras, C., Quix, C., Jarke, M.: Data lakes: a survey of functions and systems. IEEE TKDE 35(12), 12571\u201312590 (2023)","journal-title":"IEEE TKDE"},{"key":"13_CR8","unstructured":"Hassan, M.M., et. al.: ChatGPT as your personal data scientist (2023)"},{"key":"13_CR9","unstructured":"Hollmann, N., et al.: Large language models for automated data science: Introducing caafe for context-aware automated feature engineering. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Hoseini, S., Ali, A., Shaker, H., Quix, C.: SEDAR: a semantic data reservoir for heterogeneous datasets. In: CIKM 2023, ACM (2023)","DOI":"10.1145\/3583780.3614753"},{"key":"13_CR11","first-page":"100413","volume":"10","author":"S Hoseini","year":"2022","unstructured":"Hoseini, S., et al.: Automated defect detection for coatings via height profiles obtained by laser-scanning microscopy. MLWA 10, 100413 (2022)","journal-title":"MLWA"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Hoseini, S., et. al.: Coatings intelligence: data-driven automation for chemistry 4.0. In: 2024 IEEE 7th (ICPS), pp.\u00a01\u20138 (2024)","DOI":"10.1109\/ICPS59941.2024.10640053"},{"key":"13_CR13","unstructured":"Huang, Q., Vora, J., Liang, P., Leskovec, J.: Benchmarking large language models as AI research agents (2023)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Jain, A., et al.: Overview and importance of data quality for machine learning tasks. In: Proceedings of ACM SIGKDD, pp. 3561\u20133562 (2020)","DOI":"10.1145\/3394486.3406477"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Karmaker, S.K., et al.: Automl to date and beyond: challenges and opportunities. ACM Comput. Surv. 54(8) (2021)","DOI":"10.1145\/3470918"},{"key":"13_CR16","doi-asserted-by":"publisher","first-page":"9598","DOI":"10.1109\/ACCESS.2018.2888601","volume":"7","author":"Y Khan","year":"2019","unstructured":"Khan, Y., Zimmermann, A., Jha, A., Gadepally, V., d\u2019Aquin, M., Sahay, R.: One size does not fit all: querying web polystores. IEEE Access 7, 9598\u20139617 (2019)","journal-title":"IEEE Access"},{"key":"13_CR17","unstructured":"Liu, H., Ning, R., Teng, Z., Liu, J., Zhou, Q., Zhang, Y.: Evaluating the logical reasoning ability of ChatGPT and gpt-4. arXiv preprint arXiv:2304.03439 (2023)"},{"key":"13_CR18","unstructured":"Liu, S., Gao, C., Li, Y.: Large language model agent for hyper-parameter optimization. arXiv preprint arXiv:2402.01881 (2024)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Schelter, S., et. al.: Unit testing data with deequ. In: SIGMOD. ACM (2019)","DOI":"10.1145\/3299869.3320210"},{"key":"13_CR20","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/978-3-031-42914-9_17","volume-title":"ADBIS","author":"M Schlegel","year":"2023","unstructured":"Schlegel, M., Sattler, K.: Extracting provenance of machine learning experiment pipeline artifacts. In: Abell\u00f3, A., Vassiliadis, P., Romero, O., Wrembel, R. (eds.) ADBIS. LNCS, vol. 13985, pp. 238\u2013251. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-42914-9_17"},{"key":"13_CR21","unstructured":"Tornede, A., et al.: Automl in the age of large language models: Current challenges, future opportunities and risks. arXiv preprint arXiv:2306.08107 (2023)"},{"key":"13_CR22","unstructured":"Wei, L., He, Z., Zhao, H., Yao, Q.: Unleashing the power of graph learning through llm-based autonomous agents (2023)"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Yang, Z., , et. al.: Autommlab: automatically generating deployable models from language instructions for computer vision tasks (2024)","DOI":"10.1609\/aaai.v39i21.34358"},{"issue":"4","key":"13_CR24","first-page":"39","volume":"41","author":"M Zaharia","year":"2018","unstructured":"Zaharia, M., et al.: Accelerating the machine learning lifecycle with MLflow. IEEE Data Eng. Bull. 41(4), 39\u201345 (2018)","journal-title":"IEEE Data Eng. Bull."},{"key":"13_CR25","first-page":"671","volume":"19","author":"G Zhang","year":"2021","unstructured":"Zhang, G., et al.: Deep learning-based automated characterization of crosscut tests for coatings via image segmentation. JCTR 19, 671\u2013683 (2021)","journal-title":"JCTR"},{"key":"13_CR26","unstructured":"Zhang, L., et al.: Mlcopilot: unleashing the power of large language models in solving machine learning tasks. arXiv preprint arXiv:2304.14979 (2023)"},{"key":"13_CR27","unstructured":"Zhang, S., Gong, C., Wu, L., Liu, X., Zhou, M.: AutoML-GPT: automatic machine learning with GPT. arXiv preprint arXiv:2305.02499 (2023)"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Analysis-oriented metadata for data lakes. In: Proceedings of the 25th IDEAS, pp. 194\u2013203. ACM (2021)","DOI":"10.1145\/3472163.3472273"}],"container-title":["Lecture Notes in Computer Science","Advances in Databases and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70626-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T05:43:03Z","timestamp":1763962983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70626-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031706288","9783031706264"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70626-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADBIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Advances in Databases and Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bayonne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adbis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.sigappfr.org\/adbis2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}