{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:28:55Z","timestamp":1743085735491,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031434266"},{"type":"electronic","value":"9783031434273"}],"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\/978-3-031-43427-3_2","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T21:01:41Z","timestamp":1694898101000},"page":"19-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Class-Conditional Label Noise in\u00a0Astroparticle Physics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5515-6278","authenticated-orcid":false,"given":"Mirko","family":"Bunse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4012-4502","authenticated-orcid":false,"given":"Lukas","family":"Pfahler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"2_CR1","unstructured":"Acharya, B.S., et al.: Science with the Cherenkov telescope array. World Sci. (2018)"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s10686-011-9247-0","volume":"32","author":"M Actis","year":"2011","unstructured":"Actis, M., Agnetta, G., Aharonian, F., Akhperjanian, A., Aleksi\u0107, J., et al.: Design concepts for the Cherenkov telescope array CTA: an advanced facility for ground-based high-energy gamma-ray astronomy. Exper. Astron. 32(3), 193\u2013316 (2011). https:\/\/doi.org\/10.1007\/s10686-011-9247-0","journal-title":"Exper. Astron."},{"issue":"3","key":"2_CR3","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1051\/0004-6361:20065351","volume":"457","author":"F Aharonian","year":"2006","unstructured":"Aharonian, F., Akhperjanian, A., Bazer-Bachi, A., Beilicke, M., Benbow, W., et al.: Observations of the crab nebula with HESS. Astron. Astrophys. 457(3), 899\u2013915 (2006)","journal-title":"Astron. Astrophys."},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Anderhub, H., Backes, M., Biland, A., Boccone, V., Braun, I., et al.: Design and operation of FACT-the first G-APD Cherenkov telescope. J. Inst. 8(06) (2013). https:\/\/doi.org\/10.1088\/1748-0221\/8\/06\/p06008","DOI":"10.1088\/1748-0221\/8\/06\/p06008"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Blum, A., Mitchell, T.M.: Combining labeled and unlabeled data with co-training. In: Conference on Computing Learning Theory, pp. 92\u2013100. ACM (1998). https:\/\/doi.org\/10.1145\/279943.279962","DOI":"10.1145\/279943.279962"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Bock, R., et al.: Methods for multidimensional event classification: a case study using images from a Cherenkov gamma-ray telescope. Nucl. Inst. and Meth. in Phys. Res. Sec. A 516(2\u20133), 511\u2013528 (2004). https:\/\/doi.org\/10.1016\/j.nima.2003.08.157","DOI":"10.1016\/j.nima.2003.08.157"},{"key":"2_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-319-23461-8_7","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"C Bockermann","year":"2015","unstructured":"Bockermann, C., et al.: Online analysis of high-volume data streams in astroparticle physics. In: Bifet, A., et al. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9286, pp. 100\u2013115. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23461-8_7"},{"key":"2_CR8","unstructured":"Buja, A., Stuetzle, W., Shen, Y.: Loss functions for binary class probability estimation and classification: structure and applications. Tech. rep., University of Pennsylvania (2005)"},{"key":"2_CR9","first-page":"1","volume":"7","author":"J Dem\u0161ar","year":"2006","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"2_CR10","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1146\/annurev.nucl.012809.104544","volume":"61","author":"R Engel","year":"2011","unstructured":"Engel, R., Heck, D., Pierog, T.: Extensive air showers and hadronic interactions at high energy. Ann. Rev. Nucl. Part. Sci. 61(1), 467\u2013489 (2011). https:\/\/doi.org\/10.1146\/annurev.nucl.012809.104544","journal-title":"Ann. Rev. Nucl. Part. Sci."},{"key":"2_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-5422-5","author":"B Falkenburg","year":"2012","unstructured":"Falkenburg, B., Rhode, W.: From ultra rays to astroparticles: a historical introduction to astroparticle physics. Springer (2012). https:\/\/doi.org\/10.1007\/978-94-007-5422-5","journal-title":"Springer"},{"key":"2_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-98074-4","volume-title":"Learning from Imbalanced Data Sets","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez, A., Garc\u00eda, S., Galar, M., Prati, R.C., Krawczyk, B., Herrera, F.: Learning from Imbalanced Data Sets. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-98074-4"},{"issue":"1","key":"2_CR13","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1146\/annurev-nucl-102014-022036","volume":"65","author":"S Funk","year":"2015","unstructured":"Funk, S.: Ground- and space-based gamma-ray astronomy. Ann. Rev. Nucl. Part. Sci. 65(1), 245\u2013277 (2015). https:\/\/doi.org\/10.1146\/annurev-nucl-102014-022036","journal-title":"Ann. Rev. Nucl. Part. Sci."},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.neucom.2014.09.081","volume":"160","author":"A Ghosh","year":"2015","unstructured":"Ghosh, A., Manwani, N., Sastry, P.S.: Making risk minimization tolerant to label noise. Neurocomput. 160, 93\u2013107 (2015). https:\/\/doi.org\/10.1016\/j.neucom.2014.09.081","journal-title":"Neurocomput."},{"key":"2_CR15","unstructured":"Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. Adv. in Neur. Inform. Process. Syst., 8536\u20138546 (2018)"},{"key":"2_CR16","unstructured":"Koyejo, O., Natarajan, N., Ravikumar, P., Dhillon, I.S.: Consistent binary classification with generalized performance metrics. Adv. in Neur. Inform. Process. Syst., 2744\u20132752 (2014)"},{"key":"2_CR17","unstructured":"Lemaitre, G., Nogueira, F., Aridas, C.K.: Imbalanced-learn: a Python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18, 17:1\u201317:5 (2017)"},{"key":"2_CR18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1086\/161295","volume":"272","author":"TP Li","year":"1983","unstructured":"Li, T.P., Ma, Y.Q.: Analysis methods for results in gamma-ray astronomy. Astrophys. J. 272, 317\u2013324 (1983)","journal-title":"Astrophys. J."},{"key":"2_CR19","unstructured":"Li, X., Liu, T., Han, B., Niu, G., Sugiyama, M.: Provably end-to-end label-noise learning without anchor points. In: International Conference on Machine Learning Research, vol. 139, pp. 6403\u20136413. PMLR (2021)"},{"key":"2_CR20","unstructured":"Ma, X., Huang, H., Wang, Y., Romano, S., Erfani, S.M., Bailey, J.: Normalized loss functions for deep learning with noisy labels. In: International Conference on Machine Learning Proceedings of Machine Learning Research, vol. 119, pp. 6543\u20136553. PMLR (2020)"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Martschei, D., Feindt, M., Honc, S., Wagner-Kuhr, J.: Advanced event reweighting using multivariate analysis. J. of Phys.: Conf. Ser. 368 (2012). https:\/\/doi.org\/10.1088\/1742-6596\/368\/1\/012028","DOI":"10.1088\/1742-6596\/368\/1\/012028"},{"key":"2_CR22","unstructured":"Menon, A.K., Narasimhan, H., Agarwal, S., Chawla, S.: On the statistical consistency of algorithms for binary classification under class imbalance. In: International Conference on Machine Learning JMLR Workshop and Conference Proceedings, vol. 28, pp. 603\u2013611 (2013)"},{"issue":"8\u201310","key":"2_CR23","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1007\/s10994-018-5715-3","volume":"107","author":"AK Menon","year":"2018","unstructured":"Menon, A.K., van Rooyen, B., Natarajan, N.: Learning from binary labels with instance-dependent noise. Mach. Learn. 107(8\u201310), 1561\u20131595 (2018). https:\/\/doi.org\/10.1007\/s10994-018-5715-3","journal-title":"Mach. Learn."},{"key":"2_CR24","unstructured":"Menon, A.K., van Rooyen, B., Ong, C.S., Williamson, R.C.: Learning from corrupted binary labels via class-probability estimation. In: International Conference on Machine Learning JMLR Workshop and Conference Proceedings, vol. 37, pp. 125\u2013134 (2015)"},{"issue":"11","key":"2_CR25","doi-asserted-by":"publisher","first-page":"2484","DOI":"10.1109\/TKDE.2017.2739739","volume":"29","author":"V Mithal","year":"2017","unstructured":"Mithal, V., Nayak, G., Khandelwal, A., Kumar, V., Oza, N.C., Nemani, R.R.: RAPT: rare class prediction in absence of true labels. IEEE Trans. Knowl. Data Eng. 29(11), 2484\u20132497 (2017). https:\/\/doi.org\/10.1109\/TKDE.2017.2739739","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2_CR26","unstructured":"Narasimhan, H., Vaish, R., Agarwal, S.: On the statistical consistency of plug-in classifiers for non-decomposable performance measures. In: Advances in Neural Information Processing Systems, pp. 1493\u20131501 (2014)"},{"key":"2_CR27","unstructured":"Natarajan, N., Dhillon, I.S., Ravikumar, P., Tewari, A.: Learning with noisy labels. In: Advances in Neural Information Processing Systems, pp. 1196\u20131204 (2013)"},{"key":"2_CR28","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1613\/jair.1.12125","volume":"70","author":"CG Northcutt","year":"2021","unstructured":"Northcutt, C.G., Jiang, L., Chuang, I.L.: Confident learning: estimating uncertainty in dataset labels. J. Artif. Intell. Res. 70, 1373\u20131411 (2021). https:\/\/doi.org\/10.1613\/jair.1.12125","journal-title":"J. Artif. Intell. Res."},{"key":"2_CR29","doi-asserted-by":"publisher","unstructured":"Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Conference on Computer Vision and Pattern Recognition, pp. 2233\u20132241. IEEE (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.240","DOI":"10.1109\/CVPR.2017.240"},{"key":"2_CR30","unstructured":"Scott, C., Blanchard, G., Handy, G.: Classification with asymmetric label noise: consistency and maximal denoising. In: Annual Conference on Learning Theory JMLR Workshop and Conference Proceedings, vol. 30, pp. 489\u2013511. JMLR.org (2013)"},{"key":"2_CR31","doi-asserted-by":"publisher","unstructured":"Tridon, D.B., et al.: The MAGIC-II gamma-ray stereoscopic telescope system. Nucl. Inst. Meth. in Phys. Res. Sec. A 623(1), 437\u2013439 (2010). https:\/\/doi.org\/10.1016\/j.nima.2010.03.028","DOI":"10.1016\/j.nima.2010.03.028"},{"key":"2_CR32","unstructured":"Wakely, S.P., Horan, D.: TeVCat: an online catalog for very high energy gamma-ray astronomy. In: International Cosmic Ray Conference, vol. 3, pp. 1341\u20131344 (2008)"},{"key":"2_CR33","unstructured":"Xia, X., Liu, T., Wang, N., Han, B., Gong, C., et al.: Are anchor points really indispensable in label-noise learning? In: Advances in Neural Information Processing Systems, pp. 6835\u20136846 (2019)"},{"key":"2_CR34","unstructured":"Yao, Y., Liu, T., Han, B., Gong, M., Deng, J., et al.: Dual T: Reducing estimation error for transition matrix in label-noise learning. In: Advances in Neural Information Processing Systems (2020)"},{"key":"2_CR35","unstructured":"Ye, N., Chai, K.M.A., Lee, W.S., Chieu, H.L.: Optimizing F-measure: a tale of two approaches. In: International Conference on Machine Learning Omnipress (2012)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43427-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T21:03:33Z","timestamp":1694898213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43427-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434266","9783031434273"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43427-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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":"Label noise, if not mitigated, can easily lead to the learning of incorrect prediction models, which is a particular danger for safety-critical applications. Moreover, label noise can perpetuate and amplify existing societal biases if appropriate countermeasures are not taken. The existence of these risks crucially requires research on the effects and the mitigation of different kinds of label noise. In this regard, we contribute a characterization and mitigation of PK-CCN, a novel instance of class-conditional label noise.Successful mitigation techniques can tempt stakeholders to take the risks of label noise even if alternative solutions exist. In fact, we advocate the employment of PK-CCN data in a use case where training data is otherwise obtained from simulations. In spite of such alternative solutions, a careful consideration of all risks is morally required. In our use case, the risks of learning from simulations are still vague while we have clearly described the effects of PK-CCN and have mitigated them through learning algorithms that are proven to be consistent. Our algorithms result in a reduction of computational requirements, which translates to a reduction in energy consumption. This improvement is a desirable property for combating climate change. We emphasize that other cases of label noise can involve risks that require different considerations.Astroparticle physics is a research field that is concerned with advancing our understanding of the cosmos and fundamental physics. While a deep understanding of the cosmos can inspire us to appreciate nature and take better care of our planet, the understanding of fundamental physics can eventually contribute to the development of technologies that improve the lives of many.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Implications"}},{"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)"}}]}}