{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T23:09:07Z","timestamp":1778368147395,"version":"3.51.4"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032191014","type":"print"},{"value":"9783032191021","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-19102-1_21","type":"book-chapter","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:16:40Z","timestamp":1778365000000},"page":"344-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Dataset Shift via\u00a0Smart Augmentation with\u00a0Conditional Diffusion Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-4922-5641","authenticated-orcid":false,"given":"Lorenzo","family":"Peracchio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4979-2907","authenticated-orcid":false,"given":"Gabriele","family":"Santangelo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7007-0862","authenticated-orcid":false,"given":"Giovanna","family":"Nicora","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5917-5307","authenticated-orcid":false,"given":"Barbara","family":"Draghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5105-3506","authenticated-orcid":false,"given":"Allan","family":"Tucker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-9808","authenticated-orcid":false,"given":"Riccardo","family":"Bellazzi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-0409","authenticated-orcid":false,"given":"Arianna","family":"Dagliati","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,10]]},"reference":[{"key":"21_CR1","unstructured":"Ahmed, C.F., Lachiche, N., Charnay, C., Braud, A.: Dataset shift in a real-life dataset. In: ECML-PKDD workshop LMCE (2014)"},{"key":"21_CR2","doi-asserted-by":"publisher","unstructured":"Al-Bahrani, R., et al.: Sigrnn: synthetic minority instances generation in imbalanced datasets using a recurrent neural network. In: Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - ICPRAM, pp. 349\u2013356. INSTICC, SciTePress (2021). https:\/\/doi.org\/10.5220\/0010348103490356","DOI":"10.5220\/0010348103490356"},{"key":"21_CR3","first-page":"453","volume":"1","author":"S Barocas","year":"2020","unstructured":"Barocas, S., Hardt, M., Narayanan, A.: Fairness and machine learning. Recommender syst. handb. 1, 453\u2013459 (2020)","journal-title":"Recommender syst. handb."},{"key":"21_CR4","unstructured":"Cui, L., Li, H., Chen, K., Shou, L., Chen, G.: Tabular data augmentation for machine learning: progress and prospects of embracing generative AI (2024). https:\/\/arxiv.org\/abs\/2407.21523"},{"issue":"6","key":"21_CR5","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1161\/CIRCULATIONAHA.107.699579","volume":"117","author":"RB D\u2019Agostino","year":"2008","unstructured":"D\u2019Agostino, R.B., et al.: General cardiovascular risk profile for use in primary care. Circulation 117(6), 743\u2013753 (2008). https:\/\/doi.org\/10.1161\/CIRCULATIONAHA.107.699579","journal-title":"Circulation"},{"key":"21_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114582","volume":"174","author":"J Engelmann","year":"2021","unstructured":"Engelmann, J., Lessmann, S.: Conditional wasserstein gan-based oversampling of tabular data for imbalanced learning. Expert Syst. Appl. 174, 114582 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.114582","journal-title":"Expert Syst. Appl."},{"key":"21_CR7","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR8","doi-asserted-by":"publisher","unstructured":"Kim, J., et al.: Sos: score-based oversampling for tabular data. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD \u201922, pp. 762\u2013772. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3534678.3539454","DOI":"10.1145\/3534678.3539454"},{"key":"21_CR9","unstructured":"Kotelnikov, A., Baranchuk, D., Rubachev, I., Babenko, A.: Tabddpm: modelling tabular data with diffusion models. In: Proceedings of the 40th International Conference on Machine Learning, ICML\u201923. JMLR.org (2023)"},{"issue":"9","key":"21_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3555803","volume":"55","author":"B Li","year":"2023","unstructured":"Li, B., et al.: Trustworthy AI: from principles to practices. ACM Comput. Surv. 55(9), 1\u201346 (2023)","journal-title":"ACM Comput. Surv."},{"key":"21_CR11","doi-asserted-by":"publisher","unstructured":"Liu, T., Fan, J., Tang, N., Li, G., Du, X.: Controllable tabular data synthesis using diffusion models. Proc. ACM Manag. Data 2(1) (2024). https:\/\/doi.org\/10.1145\/3639283","DOI":"10.1145\/3639283"},{"key":"21_CR12","unstructured":"Madiega, T.: Artificial intelligence act (2021)"},{"key":"21_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2022.121763","volume":"181","author":"N Omrani","year":"2022","unstructured":"Omrani, N., Rivieccio, G., Fiore, U., Schiavone, F., Agreda, S.G.: To trust or not to trust? An assessment of trust in ai-based systems: concerns, ethics and contexts. Technol. Forecast. Soc. Chang. 181, 121763 (2022)","journal-title":"Technol. Forecast. Soc. Chang."},{"key":"21_CR14","unstructured":"Peracchio, L.: Relai: a python library to compute the pointwise reliability of machine learning predictions (2025). https:\/\/rel-doc.readthedocs.io\/en\/latest\/"},{"key":"21_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.105857","volume":"197","author":"L Peracchio","year":"2025","unstructured":"Peracchio, L., et al.: Relai: an automated approach to judge pointwise ml prediction reliability. Int. J. Med. Inf. 197, 105857 (2025). https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.105857","journal-title":"Int. J. Med. Inf."},{"key":"21_CR16","unstructured":"Philpott, D.: A Guide to Federal Terms and Acronyms. Bernan Press (2017)"},{"key":"21_CR17","unstructured":"Qui\u00f1onero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D.: Dataset Shift in Machine Learning. MIT Press (2022)"},{"key":"21_CR18","doi-asserted-by":"publisher","unstructured":"Rawas, S.: AI: the future of humanity. Disc. Artif. Intell. 4(1) (2024). https:\/\/doi.org\/10.1007\/s44163-024-00118-3","DOI":"10.1007\/s44163-024-00118-3"},{"issue":"6088","key":"21_CR19","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986). https:\/\/doi.org\/10.1038\/323533a0","journal-title":"Nature"},{"key":"21_CR20","unstructured":"Salimans, T.H.J., et\u00a0al.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop DGMs Applications, vol.\u00a02 (2021)"},{"key":"21_CR21","doi-asserted-by":"publisher","unstructured":"Santangelo, G., Nicora, G., Bellazzi, R., Dagliati, A.: How good is your synthetic data? Synthro, a dashboard to evaluate and benchmark synthetic tabular data. BMC Med. Inf. Decis. Mak. 25(1), 89 (2025). https:\/\/doi.org\/10.1186\/s12911-024-02731-9","DOI":"10.1186\/s12911-024-02731-9"},{"key":"21_CR22","unstructured":"Saria, S., Subbaswamy, A.: Tutorial: safe and reliable machine learning. arXiv preprint arXiv:1904.07204 (2019)"},{"key":"21_CR23","unstructured":"Shi, J., Xu, M., Hua, H., Zhang, H., Ermon, S., Leskovec, J.: Tabdiff: a mixed-type diffusion model for tabular data generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"issue":"12","key":"21_CR24","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1038\/s41551-022-00898-y","volume":"6","author":"A Zhang","year":"2022","unstructured":"Zhang, A., Xing, L., Zou, J., Wu, J.C.: Shifting machine learning for healthcare from development to deployment and from models to data. Nat. Biomed. Eng. 6(12), 1330\u20131345 (2022)","journal-title":"Nat. Biomed. Eng."},{"issue":"4","key":"21_CR25","doi-asserted-by":"publisher","first-page":"4396","DOI":"10.1109\/TPAMI.2022.3195549","volume":"45","author":"K Zhou","year":"2023","unstructured":"Zhou, K., Liu, Z., Qiao, Y., Xiang, T., Loy, C.C.: Domain generalization: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4396\u20134415 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3195549","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-19102-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T22:16:42Z","timestamp":1778365002000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-19102-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032191014","9783032191021"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-19102-1_21","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}