{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T14:24:52Z","timestamp":1780583092760,"version":"3.54.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T00:00:00Z","timestamp":1651622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001663","name":"Volkswagen Foundation","doi-asserted-by":"publisher","award":["IMPACT"],"award-info":[{"award-number":["IMPACT"]}],"id":[{"id":"10.13039\/501100001663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["05M20PBA"],"award-info":[{"award-number":["05M20PBA"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IS19080 A"],"award-info":[{"award-number":["01IS19080 A"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Federal state government of North Rhine-Westphalia","award":["Bias von KI-Modelle bei der Informationsbildung und deren Implikationen in der Wirtschaft"],"award-info":[{"award-number":["Bias von KI-Modelle bei der Informationsbildung und deren Implikationen in der Wirtschaft"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2023,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Many of today\u2019s decision making systems deployed in the real world are not static\u2014they are changing and adapting over time, a phenomenon known as model adaptation takes place. Because of their wide reaching influence and potentially serious consequences, the need for transparency and interpretability of AI-based decision making systems is widely accepted and thus have been worked on extensively\u2014e.g. a very prominent class of explanations are contrasting explanations which try to mimic human explanations. However, usually, explanation methods assume a static system that has to be explained. Explaining non-static systems is still an open research question, which poses the challenge how to explain model differences, adaptations and changes. In this contribution, we propose and (empirically) evaluate a general framework for explaining model adaptations and differences by contrasting explanations. We also propose a method for automatically finding regions in data space that are affected by a given model adaptation\u2014i.e. regions where the internal reasoning of the other (e.g. adapted) model changed\u2014and thus should be explained. Finally, we also propose a regularization for model adaptations to ensure that the internal reasoning of the adapted model does not change in an unwanted way.<\/jats:p>","DOI":"10.1007\/s11063-022-10826-5","type":"journal-article","created":{"date-parts":[[2022,5,4]],"date-time":"2022-05-04T04:07:05Z","timestamp":1651637225000},"page":"5273-5297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Contrasting Explanations for Understanding and Regularizing Model Adaptations"],"prefix":"10.1007","volume":"55","author":[{"given":"Andr\u00e9","family":"Artelt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian","family":"Hinder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerie","family":"Vaquet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Feldhans","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barbara","family":"Hammer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,4]]},"reference":[{"key":"10826_CR1","unstructured":"Stalidis P, Semertzidis T, Daras P (2018) Examining deep learning architectures for crime classification and prediction. arXiv:1812.00602"},{"key":"10826_CR2","doi-asserted-by":"crossref","unstructured":"Khandani AE, Kim AJ, Lo A (2010) Consumer credit-risk models via machine-learning algorithms. J Bank Finance 34(11)","DOI":"10.1016\/j.jbankfin.2010.06.001"},{"key":"10826_CR3","unstructured":"Waddell K (2016) How algorithms can bring down minorities\u2019 credit scores. The Atlantic"},{"key":"10826_CR4","doi-asserted-by":"crossref","unstructured":"Leslie D (2019) Understanding artificial intelligence ethics and safety. CoRR arXiv:1906.05684","DOI":"10.2139\/ssrn.3403301"},{"key":"#cr-split#-10826_CR5.1","unstructured":"Parliament E, council (2016) General Data Protection Regulation: Regulation"},{"key":"#cr-split#-10826_CR5.2","unstructured":"(EU) 2016\/679 of the European Parliament. Off J Eur Union"},{"key":"10826_CR6","unstructured":"Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A (2019) A survey on bias and fairness in machine learning. CoRR arXiv:1908.09635"},{"key":"10826_CR7","unstructured":"Caton S, Haas C (2020) Fairness in machine learning: a survey. CoRR (2020) arXiv:2010.04053"},{"key":"10826_CR8","doi-asserted-by":"crossref","unstructured":"Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D (2018) A survey of methods for explaining black box models. ACM Comput Surv 51(5)","DOI":"10.1145\/3236009"},{"key":"10826_CR9","unstructured":"Tjoa E, Guan C (2019) A survey on explainable artificial intelligence (XAI): towards medical XAI. CoRR arXiv:1907.07374"},{"key":"10826_CR10","unstructured":"Samek W, Wiegand T, M\u00fcller K (2017) Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. CoRR. arXiv:1708.08296"},{"key":"10826_CR11","doi-asserted-by":"crossref","unstructured":"Molnar C (2019) Interpretable machine learning","DOI":"10.21105\/joss.00786"},{"key":"10826_CR12","unstructured":"Greenwell BM, Boehmke BC, McCarthy AJ (2018) A simple and effective model-based variable importance measure. CoRR. arXiv:1805.04755"},{"key":"10826_CR13","unstructured":"Fisher A, Rudin C, Dominici F (2018) All models are wrong but many are useful: variable importance for Black-Box, proprietary, or misspecified prediction models, using Model Class Reliance. arXiv e-prints, 1801-01489. arXiv:1801.01489 [stat.ME]"},{"key":"10826_CR14","doi-asserted-by":"crossref","unstructured":"Zhao Q, Hastie T (2019) Causal interpretations of black-box models. J Bus Econ Stat","DOI":"10.1080\/07350015.2019.1624293"},{"key":"10826_CR15","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) \u201cWhy should i trust you?\u201d: Explaining the predictions of any classifier. KDD \u201916. ACM, New York","DOI":"10.1145\/2939672.2939778"},{"key":"10826_CR16","doi-asserted-by":"crossref","unstructured":"Aamodt A, Plaza E (1994) Case-based reasoning: foundational issues, methodological variations, and systemapproaches. AI Communications","DOI":"10.3233\/AIC-1994-7104"},{"key":"10826_CR17","doi-asserted-by":"crossref","unstructured":"Wachter S, Mittelstadt BD, Russell C (2017) Counterfactual explanations without opening the black box: automated decisions and the GDPR. CoRR arXiv:1711.00399","DOI":"10.2139\/ssrn.3063289"},{"key":"10826_CR18","unstructured":"Verma S, Dickerson J, Hines K (2020) Counterfactual explanations for machine learning: a review"},{"key":"10826_CR19","unstructured":"Kim B, Koyejo O, Khanna R (2016) Examples are not enough, learn to criticize! criticism for interpretability. In: Advances in neural information processing systems, 29"},{"key":"10826_CR20","doi-asserted-by":"crossref","unstructured":"Byrne RMJ (2019) Counterfactuals in explainable artificial intelligence (xai): evidence from human reasoning. In: IJCAI-19","DOI":"10.24963\/ijcai.2019\/876"},{"key":"10826_CR21","unstructured":"Pedapati T, Balakrishnan A, Shanmugam K, Dhurandhar A (2020) Learning global transparent models consistent with local contrastive explanations. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in neural information processing systems, vol 33. Curran Associates, Inc"},{"key":"10826_CR22","unstructured":"Botari T, Hvilshj F, Izbicki R, de Carvalho ACPLF (2020) MeLIME: meaningful local explanation for machine learning models"},{"key":"10826_CR23","unstructured":"Artelt A, Hammer B (2019) On the computation of counterfactual explanations: a survey. CoRR. arXiv:1911.07749"},{"key":"10826_CR24","doi-asserted-by":"crossref","unstructured":"Parisi GI, Kemker R, Part JL, Kanan C, Wermter S (2019) Continual lifelong learning with neural networks: a review. Neural Netw 113","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"10826_CR25","doi-asserted-by":"crossref","unstructured":"Venkatasubramanian S, Alfano M (2020) The philosophical basis of algorithmic recourse. FAT* \u201920","DOI":"10.1145\/3351095.3372876"},{"key":"10826_CR26","unstructured":"Sample I (2017) Computer says no: why making AIs fair, accountable and transparent is crucial. The Guardian"},{"key":"10826_CR27","doi-asserted-by":"crossref","unstructured":"Shneiderman B (2020) Bridging the gap between ethics and practice: guidelines for reliable, safe, and trustworthy human-centered ai systems. ACM Trans Interact Intell Syst 10(4)","DOI":"10.1145\/3419764"},{"key":"10826_CR28","doi-asserted-by":"crossref","unstructured":"Wortman\u00a0Vaughan J, Wallach H (2021) A human-centered agenda for intelligible machine learning","DOI":"10.7551\/mitpress\/12186.003.0014"},{"key":"10826_CR29","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.neucom.2021.04.129","volume":"470","author":"A Artelt","year":"2022","unstructured":"Artelt A, Hammer B (2022) Efficient computation of counterfactual explanations and counterfactual metrics of prototype-based classifiers. Neurocomputing 470:304\u2013317. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.129","journal-title":"Neurocomputing"},{"key":"10826_CR30","unstructured":"Hinder F, Hammer B (2020) Counterfactual explanations of concept drift"},{"key":"10826_CR31","doi-asserted-by":"crossref","unstructured":"Gama J, \u017dliobait\u0117 I, Bifet A, Pechenizkiy M, Bouchachia A (2014) A survey on concept drift adaptation. ACM Comput Surveys 46(4)","DOI":"10.1145\/2523813"},{"key":"10826_CR32","unstructured":"Dhurandhar A, Chen P, Luss R, Tu C, Ting P, Shanmugam K, Das P (2018) Explanations based on the missing: Towards contrastive explanations with pertinent negatives. In: Bengio S, Wallach HM, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems 31: annual conference on neural information processing systems 2018, NeurIPS 2018, 3\u20138 December 2018. Montr\u00e9al, Canada"},{"key":"10826_CR33","unstructured":"Dhurandhar A, Pedapati T, Balakrishnan A, Chen P, Shanmugam K, Puri R (2019) Model agnostic contrastive explanations for structured data. CoRR arXiv:1906.00117"},{"key":"10826_CR34","doi-asserted-by":"publisher","unstructured":"Artelt A, Hammer B (2021) Efficient computation of contrastive explanations. In: International joint conference on neural networks, IJCNN 2021, Shenzhen, China, July 18\u201322, 2021, pp. 1\u20139. IEEE. https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9534454","DOI":"10.1109\/IJCNN52387.2021.9534454"},{"key":"10826_CR35","unstructured":"Carlini N, Athalye A, Papernot N, Brendel W, Rauber J, Tsipras D, Goodfellow I, Madry A, Kurakin, A (2019) On evaluating adversarial robustness. arXiv preprint arXiv:1902.06705"},{"key":"10826_CR36","doi-asserted-by":"publisher","unstructured":"Artelt A, Hammer B (2020) Convex density constraints for computing plausible counterfactual explanations. In: Farkas I, Masulli P, Wermter S (eds) Artificial Neural Networks and Machine Learning\u2014ICANN 2020\u201429th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15-18, 2020, Proceedings, Part I. Lecture Notes in Computer Science, vol. 12396, pp. 353\u2013365. Springer. https:\/\/doi.org\/10.1007\/978-3-030-61609-0_28","DOI":"10.1007\/978-3-030-61609-0_28"},{"key":"10826_CR37","unstructured":"Artelt A (2019-2021) CEML: counterfactuals for explaining machine learning models\u2014a python toolbox. GitHub"},{"key":"10826_CR38","doi-asserted-by":"crossref","unstructured":"Reyes-Ortiz J, Oneto L, Sam\u00e0 A, Parra X, Anguita D (2016) Transition-aware human activity recognition using smartphones. Neurocomputing 171","DOI":"10.1016\/j.neucom.2015.07.085"},{"key":"10826_CR39","unstructured":"Statlog (German Credit Data) Data Set (1994). https:\/\/archive.ics.uci.edu\/ml\/datasets\/Statlog+%28German+Credit+Data%29"},{"key":"10826_CR40","unstructured":"Boston Housing Data Set (1978). https:\/\/archive.ics.uci.edu\/ml\/datasets\/Housing"},{"key":"10826_CR41","doi-asserted-by":"crossref","unstructured":"Artelt A, Vaquet V, Velioglu R, Hinder F, Brinkrolf J, Schilling M, Hammer B (2021) Evaluating robustness of counterfactual explanations. arXiv preprint arXiv:2103.02354","DOI":"10.1109\/SSCI50451.2021.9660058"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10826-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10826-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10826-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T16:09:07Z","timestamp":1696003747000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10826-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,4]]},"references-count":42,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["10826"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10826-5","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"value":"1370-4621","type":"print"},{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,4]]},"assertion":[{"value":"4 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}