{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T14:08:08Z","timestamp":1791209288940,"version":"4.1.0"},"reference-count":9,"publisher":"Cambridge University Press (CUP)","issue":"S397","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"unspecified","delay-in-days":430,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Proc. IAU"],"published-print":{"date-parts":[[2025,8]]},"abstract":"Abstract<\/jats:title>\n Machine learning (ML) is increasingly important in astrophysics, enabling the analysis of large, complex datasets for tasks such as stellar classification and gravitational wave detection. Yet many ML models are highly non-linear, with intricate feature interactions that make them difficult to interpret and often viewed as \u201cblack boxes.\u201d Interpretability is therefore essential for ensuring trust, scientific validity, but also for uncovering new scientific insights.<\/jats:p>\n Global feature effect methods address this by quantifying how input features influence model outputs on average. However, such explanations may be misleading when strong interactions cause individual behaviours to deviate from the average. Regional effect plots mitigate this by partitioning the feature space into more homogeneous subspaces, producing more accurate effect estimates.<\/jats:p>\n \n This talk reviews global feature effect methods, introduces recent advances, and presents\n Effector<\/jats:italic>\n , an open-source Python package for efficiently generating accurate global and regional feature effect plots.\n <\/jats:p>","DOI":"10.1017\/s1743921325104778","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T13:49:01Z","timestamp":1791208141000},"page":"54-58","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":0,"title":["Regional Effect Plots for Machine Learning Model Interpretation"],"prefix":"10.1017","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2461-1928","authenticated-orcid":false,"given":"Christos","family":"Diou","sequence":"first","affiliation":[{"name":"Harokopio University of Athens"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasileios","family":"Gkolemis","sequence":"additional","affiliation":[{"name":"Harokopio University of Athens"},{"name":"ATHENA Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodoros","family":"Dalamagas","sequence":"additional","affiliation":[{"name":"ATHENA Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"S1743921325104778_ref3","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"S1743921325104778_ref9","unstructured":"Molnar, C. 2022. Interpretable Machine Learning. 2 edition."},{"key":"S1743921325104778_ref1","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12377"},{"key":"S1743921325104778_ref4","unstructured":"Gkolemis, V. , Dalamagas, T. , & Diou, C. Dale: Differential accumulated local effects for efficient and accurate global explanations. In Asian Conference on Machine Learning 2023,a, pp. 375\u2013390. PMLR."},{"key":"S1743921325104778_ref5","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230354"},{"key":"S1743921325104778_ref7","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2014.907095"},{"key":"S1743921325104778_ref8","first-page":"1","article-title":"Decomposing global feature effects based on feature interactions","volume":"25","author":"Herbinger","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"S1743921325104778_ref2","unstructured":"Fanaee-T, H. & Gama, J. 2013, Event labeling combining ensemble detectors and background knowledge. Progress in Artificial Intelligence, 1\u201315."},{"key":"S1743921325104778_ref6","unstructured":"Gkolemis, V. , Diou, C. , Ntoutsi, E. , Dalamagas, T. , Bischl, B. , Herbinger, J. , & Casalicchio, G. 2024, Effector: A python package for regional explanations. arXiv preprint arXiv:2404.02629."}],"container-title":["Proceedings of the International Astronomical Union"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S1743921325104778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T13:49:40Z","timestamp":1791208180000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S1743921325104778\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":9,"journal-issue":{"issue":"S397","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["S1743921325104778"],"URL":"https:\/\/doi.org\/10.1017\/s1743921325104778","relation":{},"ISSN":["1743-9213","1743-9221"],"issn-type":[{"value":"1743-9213","type":"print"},{"value":"1743-9221","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"\u00a9 The Author(s), 2026. Published by Cambridge University Press on behalf of The International Astronomical Union","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https:\/\/creativecommons.org\/licenses\/by\/4.0\/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}