{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T11:10:43Z","timestamp":1781089843058,"version":"3.54.1"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Engineering Secure Systems topic of the Helmholtz Association"},{"name":"pilot program Core Informatics at KIT (KiKIT) of HGFs"},{"name":"Italian Ministry of Education, Universities, and Research","award":["20224AJBLJ"],"award-info":[{"award-number":["20224AJBLJ"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Auton. Adapt. Syst."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>Self-adaptive systems increasingly rely on black-box predictive models, such as Neural Networks, for decision-making and adaptation planning. In this case, adaptation decisions and their potential impact on the surrounding environment are hard to explain. Further, the opaque nature of these models often involves expensive optimization techniques. The computational complexity is a consequence of the inability to directly observe or comprehend the internal mechanisms of the black-box predictive models. This requires iterative methods to explore a possibly large search space and optimize according to many objectives, creating a critical challenge in balancing effectiveness and cost.<\/jats:p>\n                  <jats:p>In this article, we propose explanation-driven self-adaptation, a novel approach that embeds model-agnostic interpretable machine learning techniques into the feedback loop. In particular, we present XDA-II, an extended version of XDA that integrates multiple explanation sources. This new version combines Partial Dependence Plots and Feature Importance to maintain interpretability while boosting efficiency. Beyond interpretability benefits, explanations become instrumental to guide adaptations through white-box optimization, which is more cost-effective than black-box optimization due to the transparency and predictable mathematical properties of the functions involved. Our empirical evaluation using six study subjects shows that XDA-II achieves more efficient convergence towards optimal adaptation solutions compared to four selected baseline methods including existing black-box methods\u2014random search, NSGA-III, and FITEST\u2014and white-box methods\u2014the predecessor XDA.<\/jats:p>","DOI":"10.1145\/3737648","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:20:28Z","timestamp":1750281628000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Self-Adaptation through Explanation-Driven White-Box Optimization"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7638-2006","authenticated-orcid":false,"given":"Francesco Renato","family":"Negri","sequence":"first","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6147-7551","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Nicolosi","sequence":"additional","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2491-5267","authenticated-orcid":false,"given":"Matteo","family":"Camilli","sequence":"additional","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3154-2438","authenticated-orcid":false,"given":"Raffaela","family":"Mirandola","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Sara Mahdavi-Hezavehi Danny Weyns Paris Avgeriou Radu Calinescu Raffaela Mirandola and Diego Perez-Palacin. 2020. Uncertainty in self-adaptive systems: A research community perspective. ACM Transactions on Autonomous and Adaptive Systems 15 4 (2020) Article 10 1\u201336.","DOI":"10.1145\/3487921"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617946.3617951"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEAMS51251.2021.00020"},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Jia Li Shiva Nejati and Mehrdad Sabetzadeh. 2022. Learning self-adaptations for IoT networks: A genetic programming approach. arXiv:2205.04352. Retrieved from https:\/\/arxiv.org\/abs\/2205.04352","DOI":"10.1145\/3524844.3528053"},{"key":"e_1_3_2_6_2","unstructured":"Danny Weyns Omid Gheibi Federico Quin and Jeroen Van Der Donckt. 2022. Deep learning for effective and efficient reduction of large adaptation spaces in self-adaptive systems. arXiv:2204.06254. Retrieved from https:\/\/arxiv.org\/abs\/2204.06254"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Omid Gheibi Danny Weyns and Federico Quin. 2021. Applying machine learning in self-adaptive systems: A systematic literature review 15 3 (Aug. 2021) Article 9 1\u201337. DOI: 10.1145\/3469440","DOI":"10.1145\/3469440"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/72.788640"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524844.3528052"},{"key":"e_1_3_2_11_2","volume-title":"Proceedings of the International Conference on Automated Software Engineering (ASE \u201922)","author":"Camilli Matteo","year":"2023","unstructured":"Matteo Camilli, Raffaela Mirandola, and Patrizia Scandurra. 2023. XSA: Explainable self-adaptation. In Proceedings of the International Conference on Automated Software Engineering (ASE \u201922). ACM."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643915.3644085"},{"key":"e_1_3_2_13_2","volume-title":"Interpretable Machine Learning","author":"Molnar Christoph","year":"2022","unstructured":"Christoph Molnar. 2022. Interpretable Machine Learning (2nd ed.). Retrieved from https:\/\/christophm.github.io\/interpretable-ml-book","edition":"2"},{"key":"e_1_3_2_14_2","unstructured":"Aaron Fisher Cynthia Rudin and Francesca Dominici. 2019. All models are wrong but many are useful: Learning a variable\u2019s importance by studying an entire class of prediction models simultaneously. arXiv:1801.01489. Retrieved from https:\/\/arxiv.org\/abs\/1801.01489"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35813-5_9"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2023.107286"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/SEAMS.2019.00031"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524844.3528056"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3584364"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380365"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281535"},{"issue":"1","key":"e_1_3_2_22_2","first-page":"3","article-title":"Supervised machine learning: A review of classification techniques","volume":"160","author":"Kotsiantis Sotiris B.","year":"2007","unstructured":"Sotiris B. Kotsiantis, Ioannis Zaharakis, and P. Pintelas. 2007. Supervised machine learning: A review of classification techniques. Emerging Artificial Intelligence Applications in Computer Engineering 160, 1 (2007), 3\u201324.","journal-title":"Emerging Artificial Intelligence Applications in Computer Engineering"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295230"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.5555\/1622767.1622768"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238192"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3440119"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985795"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"issue":"2","key":"e_1_3_2_30_2","first-page":"101","article-title":"A critique and improvement of the \u201ccl\u201d common language effect size statistics of McGraw and Wong","volume":"25","author":"Vargha Andr\u00e1s","year":"2000","unstructured":"Andr\u00e1s Vargha and Harold D. Delaney. 2000. A critique and improvement of the \u201ccl\u201d common language effect size statistics of McGraw and Wong. Journal of Educational and Behavioral Statistics 25, 2 (2000), 101\u2013132. Retrieved from http:\/\/www.jstor.org\/stable\/1165329","journal-title":"Journal of Educational and Behavioral Statistics"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1424"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102301"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103473"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583558"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678580"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2021.106800"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86044-8_4"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Larissa Chazette Wasja Brunotte and Timo Speith. 2021. Exploring explainability: A definition a model and a knowledge catalogue. In Proceedings of the IEEE 29th International Requirements Engineering Conference (RE\u201921) Notre Dame IN USA 197\u2013208. DOI: 10.1109\/RE51729.2021.00025","DOI":"10.1109\/RE51729.2021.00025"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/MODELS-C.2019.00084"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC51774.2021.00247"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3387939.3391592"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111538"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACSOS55765.2022.00023"},{"key":"e_1_3_2_44_2","first-page":"165","volume-title":"Proceedings of the Sun Enterprise Authentication Mechanism (SEAMS \u201920)","author":"de Lemos Rog\u00e9rio","year":"2020","unstructured":"Rog\u00e9rio de Lemos. 2020. Human in the loop: What is the point of no return? In Proceedings of the Sun Enterprise Authentication Mechanism (SEAMS \u201920). ACM, 165\u2013166."},{"issue":"4","key":"e_1_3_2_45_2","article-title":"Architectural framework for exploring adaptive human-machine teaming options in simulated dynamic environments","volume":"6","author":"Madni Azad M.","year":"2018","unstructured":"Azad M. Madni and Carla C. Madni. 2018. Architectural framework for exploring adaptive human-machine teaming options in simulated dynamic environments. Systems 6, 4 (2018), 44.","journal-title":"Systems"},{"key":"e_1_3_2_46_2","first-page":"48","volume-title":"Proceedings of the Sun Enterprise Authentication Mechanism (SEAMS \u201921)","author":"Li Nianyu","year":"2021","unstructured":"Nianyu Li, Javier C\u00e1mara, David Garlan, Bradley R. Schmerl, and Zhi Jin. 2021. Hey! Preparing humans to do tasks in self-adaptive systems. In Proceedings of the Sun Enterprise Authentication Mechanism (SEAMS \u201921). IEEE, 48\u201358."},{"key":"e_1_3_2_47_2","first-page":"86","volume-title":"Proceedings of 2023 IEEE 20th International Conference on Software Architecture Companion","author":"Bersani Marcello M.","year":"2023","unstructured":"Marcello M. Bersani, Matteo Camilli, Livia Lestingi, Raffaela Mirandola, Matteo Rossi, and Patrizia Scandurra. 2023. Towards better trust in human-machine teaming through explainable dependability. In Proceedings of 2023 IEEE 20th International Conference on Software Architecture Companion. IEEE, 86\u201390."},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/FormaliSE58978.2023.00010"}],"container-title":["ACM Transactions on Autonomous and Adaptive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3737648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:53:09Z","timestamp":1781088789000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3737648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3737648"],"URL":"https:\/\/doi.org\/10.1145\/3737648","relation":{},"ISSN":["1556-4665","1556-4703"],"issn-type":[{"value":"1556-4665","type":"print"},{"value":"1556-4703","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"assertion":[{"value":"2024-11-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}