{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:01:40Z","timestamp":1770692500589,"version":"3.49.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031434174","type":"print"},{"value":"9783031434181","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43418-1_28","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T09:02:26Z","timestamp":1694854946000},"page":"462-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["An Empirical Evaluation of\u00a0the\u00a0Rashomon Effect in\u00a0Explainable Machine Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-9695","authenticated-orcid":false,"given":"Sebastian","family":"M\u00fcller","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8372-8251","authenticated-orcid":false,"given":"Vanessa","family":"Toborek","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7824-6647","authenticated-orcid":false,"given":"Katharina","family":"Beckh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4607-8957","authenticated-orcid":false,"given":"Matthias","family":"Jakobs","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6615-2128","authenticated-orcid":false,"given":"Christian","family":"Bauckhage","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2123-3781","authenticated-orcid":false,"given":"Pascal","family":"Welke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","volume":"6","author":"A Adadi","year":"2018","unstructured":"Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138\u201352160 (2018)","journal-title":"IEEE Access"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Alkhatib, A., Bostr\u00f6m, H., Vazirgiannis, M.: Explaining predictions by characteristic rules. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML\/PKDD) (2022)","DOI":"10.1007\/978-3-031-26387-3_24"},{"key":"28_CR3","unstructured":"Alvarez-Melis, D., Jaakkola, T.S.: On the robustness of interpretability methods. In: Workshop on Human Interpretability in Machine Learning (WHI@ICML) (2018)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Ancona, M., Ceolini, E., \u00d6ztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for deep neural networks. In: International Conference on Learning Representations, (ICLR) (2018)","DOI":"10.1007\/978-3-030-28954-6_9"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Atanasova, P., Simonsen, J.G., Lioma, C., Augenstein, I.: A diagnostic study of explainability techniques for text classification. In: Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.263"},{"key":"28_CR6","doi-asserted-by":"publisher","unstructured":"Beckh, K., et al.: Harnessing prior knowledge for explainable machine learning: an overview. In: 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), pp. 450\u2013463 (2023). https:\/\/doi.org\/10.1109\/SaTML54575.2023.00038","DOI":"10.1109\/SaTML54575.2023.00038"},{"key":"28_CR7","unstructured":"Bogun, A., Kostadinov, D., Borth, D.: Saliency diversified deep ensemble for robustness to adversaries. In: AAAI-22 Workshop on Adversarial Machine Learning and Beyond (2021)"},{"issue":"3","key":"28_CR8","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1214\/ss\/1009213726","volume":"16","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Statistical modeling: the two cultures (with comments and a rejoinder by the author). Stat. Sci. 16(3), 199\u2013231 (2001)","journal-title":"Stat. Sci."},{"key":"28_CR9","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1613\/jair.1.12228","volume":"70","author":"N Burkart","year":"2021","unstructured":"Burkart, N., Huber, M.F.: A survey on the explainability of supervised machine learning. J. Artif. Intell. Res. 70, 245\u2013317 (2021)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"DeYoung, J., et al.: ERASER: a benchmark to evaluate rationalized NLP models. In: Annual Meeting of the Association for Computational Linguistics (ACL) (2020)","DOI":"10.18653\/v1\/2020.acl-main.408"},{"issue":"4","key":"28_CR11","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1111\/coin.12410","volume":"37","author":"R ElShawi","year":"2021","unstructured":"ElShawi, R., Sherif, Y., Al-Mallah, M., Sakr, S.: Interpretability in healthcare: a comparative study of local machine learning interpretability techniques. Comput. Intell. 37(4), 1633\u20131650 (2021)","journal-title":"Comput. Intell."},{"issue":"177","key":"28_CR12","first-page":"1","volume":"20","author":"A Fisher","year":"2019","unstructured":"Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: learning a variable\u2019s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. 20(177), 1\u201381 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"28_CR13","unstructured":"Flora, M., Potvin, C., McGovern, A., Handler, S.: Comparing explanation methods for traditional machine learning models part 1: an overview of current methods and quantifying their disagreement. arXiv preprint arXiv:2211.08943 (2022)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Guidotti, R., Ruggieri, S.: Assessing the stability of interpretable models. arXiv preprint arXiv:1810.09352 (2018)","DOI":"10.1109\/IJCNN.2019.8852158"},{"key":"28_CR15","unstructured":"Han, T., Srinivas, S., Lakkaraju, H.: Which explanation should i choose? A function approximation perspective to characterizing post hoc explanations. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Hancox-Li, L.: Robustness in machine learning explanations: does it matter? In: Conference on Fairness, Accountability, and Transparency (FAT*) (2020)","DOI":"10.1145\/3351095.3372836"},{"key":"28_CR17","unstructured":"Hooker, S., Erhan, D., Kindermans, P.J., Kim, B.: A benchmark for interpretability methods in deep neural networks. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"28_CR18","doi-asserted-by":"publisher","first-page":"105507","DOI":"10.1016\/j.compag.2020.105507","volume":"174","author":"M Koklu","year":"2020","unstructured":"Koklu, M., \u00d6zkan, I.A.: Multiclass classification of dry beans using computer vision and machine learning techniques. Comput. Electron. Agric. 174, 105507 (2020)","journal-title":"Comput. Electron. Agric."},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Krishna, S., et al.: The disagreement problem in explainable machine learning: a practitioner\u2019s perspective. arXiv preprint arXiv:2202.01602 (2022)","DOI":"10.21203\/rs.3.rs-2963888\/v1"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Leventi-Peetz, A.M., Weber, K.: Rashomon effect and consistency in explainable artificial intelligence (XAI). In: Future Technologies Conference (FTC) (2022)","DOI":"10.1007\/978-3-031-18461-1_52"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Liu, F., Avci, B.: Incorporating priors with feature attribution on text classification. In: Annual Meeting of the Association for Computational Linguistics (ACL) (2019)","DOI":"10.18653\/v1\/P19-1631"},{"key":"28_CR22","unstructured":"Lundberg, S., Lee, S.I.: A Unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"28_CR23","unstructured":"Marx, C.T., Calmon, F.P., Ustun, B.: Predictive multiplicity in classification. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"28_CR24","unstructured":"Molnar, C.: Interpretable Machine Learning. 2nd edn. (2022)"},{"key":"28_CR25","unstructured":"M\u00fccke, S., Pfahler, L.: Check Mate: a sanity check for trustworthy AI. In: Lernen. Wissen. Daten. Analysen. (LWDA) (2022)"},{"key":"28_CR26","unstructured":"Neely, M., Schouten, S.F., Bleeker, M.J., Lucic, A.: order in the court: explainable AI methods prone to disagreement. arXiv preprint arXiv:2105.03287 (2021)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier. In: International Conference on Knowledge Discovery and Data Mining (KDD) (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"28_CR28","doi-asserted-by":"publisher","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","volume":"8","author":"R Roscher","year":"2020","unstructured":"Roscher, R., Bohn, B., Duarte, M.F., Garcke, J.: Explainable machine learning for scientific insights and discoveries. IEEE Access 8, 42200\u201342216 (2020)","journal-title":"IEEE Access"},{"issue":"8","key":"28_CR29","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1038\/s42256-020-0212-3","volume":"2","author":"P Schramowski","year":"2020","unstructured":"Schramowski, P., et al.: Making deep neural networks right for the right scientific reasons by interacting with their explanations. Nat. Mach. Intell. 2(8), 476\u2013486 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Semenova, L., Rudin, C., Parr, R.: On the existence of simpler machine learning models. In: Conference on Fairness, Accountability, and Transparency (FAccT) (2022)","DOI":"10.1145\/3531146.3533232"},{"issue":"3","key":"28_CR31","first-page":"262","volume":"10","author":"VG Sigillito","year":"1989","unstructured":"Sigillito, V.G., Wing, S.P., Hutton, L.V., Baker, K.B.: Classification of radar returns from the ionosphere using neural networks. Johns Hopkins APL Tech. Digest 10(3), 262\u2013266 (1989)","journal-title":"Johns Hopkins APL Tech. Digest"},{"key":"28_CR32","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"28_CR33","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., Wattenberg, M.: Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825 (2017)"},{"key":"28_CR34","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"28_CR35","doi-asserted-by":"crossref","unstructured":"Watson, M., Hasan, B.A.S., Al Moubayed, N.: Agree to disagree: when deep learning models with identical architectures produce distinct explanations. In: Winter Conference on Applications of Computer Vision (WACV) (2022)","DOI":"10.1109\/WACV51458.2022.00159"},{"key":"28_CR36","unstructured":"Wolberg, W., Street, N., Mangasarian, O.: Breast Cancer Wisconsin (Diagnostic). UCI Machine Learning Repository (1995)"},{"key":"28_CR37","unstructured":"Xin, R., Zhong, C., Chen, Z., Takagi, T., Seltzer, M., Rudin, C.: Exploring the whole rashomon set of sparse decision trees. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"28_CR38","unstructured":"Yeh, C., Hsieh, C., Suggala, A.S., Inouye, D.I., Ravikumar, P.: On the (In)fidelity and sensitivity of explanations. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"issue":"1","key":"28_CR39","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11023-021-09583-6","volume":"32","author":"C Zednik","year":"2022","unstructured":"Zednik, C., Boelsen, H.: Scientific exploration and explainable artificial intelligence. Minds Mach. 32(1), 219\u2013239 (2022)","journal-title":"Minds Mach."},{"key":"28_CR40","unstructured":"Zhang, X., Zhao, J.J., LeCun, Y.: Character-level convolutional networks for text classification. In: Advances in Neural Information Processing Systems (NeurIPS) (2015)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43418-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T13:10:25Z","timestamp":1719407425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43418-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434174","9783031434181"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43418-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"In critical contexts, where persons are directly or indirectly impacted by a model, and where explanations are used to verify that model behavior is compliant with a given standard, proper use of explanation methods is of utmost importance. Hyperparameter choices have to be validated for each model individually. For model testing and validation procedures to be reliable they have to integrate this knowledge. Our work demonstrated that it is unreasonable to expect an explanation computed for one model, to be valid for another model, however similar their performance otherwise may be. Re-using explanations from one model to give as an explanation of behavior for another model is not possible and has to be avoided in critical scenarios.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"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":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}