Accès ouvert déclaré
2025
preprint
Building Machine Learning Challenges for Anomaly Detection in Science
Elizabeth Campolongo, Y. Chou, Ekaterina Govorkova, W. Bhimji, Weilun Chao, C.J. Harris, S.‐C. Hsu, Hilmar Lapp, M. S. Neubauer, Josephine Namayanja, Aneesh C. Subramanian, David Carlyn, Subhankar Ghosh, Christopher Lawrence, Eric Moreno, Ryan Raikman, Jiaman Wu, Ziheng Zhang, Mohammad Ahmadi Gharehtoragh, S. Alonso Monsalve, M. Babicz, Furqan Baig, Namrata Banerji, William Bardon, Tyler Barna, Tanya Berger‐Wolf, Adji Bousso Dieng, Micah L. Brachman, Quentin Buat, David Hui, Phuong Cao, Franco Cerino, Yi-Chun Chang, Shivaji Chaulagain, An-Kai Chen, Deming Chen, Eric Chen, Chia-Jui Chou, Zih-Chen Ciou, Miles Cochran-Branson, M. W. Coughlin, Matteo Cremonesi, Maria C. Dadarlat, Peter T. Darch, Malina Desai, Daniel Díaz, Steven Dillmann, J. Duarte, Isla Duporge, Urbas Ekka, Saba Entezari Heravi, Fang Hao, Rian Flynn, Geoffrey Fox, E. D. D. Freed, Jing Gao, J. L. Gonski, M. J. Graham, Abolfazl Hashemi, Scott Hauck, James Hazelden, J. Peterson, Duc Hoang, Wei Hu, Mirco Huennefeld, David Hyde, Vandana P. Janeja, Nattapon Jaroenchai, Haoyi Jia, Yunfan Kang, Maksim Kholiavchenko, E. E. Khoda, S. Kim, Aditya Kumar, Bo‐Cheng Lai, Trung Le, Chi‐Wei Lee, JangHyeon Lee, Suzan van der Lee, Charles Lewis, Haitong Li, Haoyang Li, Henry Liao, Mia Liu, Xiaolin Liu, Xiulong Liu, Vladimir Lončar, Fangzheng Lyu, Ilya Makarov, Alexander Michels, Alexander Migala, Farouk Mokhtar, Mathieu Morlighem, Min Namgung, A. Novák, Andrew C. Novick, Amy L. Orsborn, Anand Padmanabhan, Sneh Pandya, A. P. Pereira Peixoto, Alex Po Leung, Sanjay Purushotham, Zhiqiang Que, M. Quinnan, Dylan Rankin, Christina Reissel, Benedikt Riedel, Dan Rubenstein, A. Sasli, Eli Shlizerman, Arushi Singh, Eric R. Sokol, Yu Su, Mitra L. Taheri, Vaibhav Thakkar, Eric S. Toberer, Rebecca Vandewalle, Arjun Verma, Ricco C. Venterea, He Wang, Jianwu Wang, Sam C. Wang, Shaowen Wang, Gordon Watts, Jason Weitz, Andrew Wildridge, Rebecca Williams, Scott Wolf, Yue Xu, Jianqi Yan, Jai Y. Yu, Yulei Zhang, Haoran Zhao, Ying Zhao, Yibo Zhong
0Citations signalées — pas une note de qualité
0Institutions déclarées
0Pays d’affiliation déclarés
Résumé fourni par la source
Scientific discoveries are often made by finding a pattern or object that was not predicted by the known rules of science. Oftentimes, these anomalous events or objects that do not conform to the norms are an indication that the rules of science governing the data are incomplete, and something new needs to be present to explain these unexpected outliers. The challenge of finding anomalies can be confounding since it requires codifying a complete knowledge of the known scientific behaviors and then projecting these known behaviors on the data to look for deviations. When utilizing machine learning, this presents a particular challenge since we require that the model not only understands scientific data perfectly but also recognizes when the data is inconsistent and out of the scope of its trained behavior. In this paper, we present three datasets aimed at developing machine learning-based anomaly detection for disparate scientific domains covering astrophysics, genomics, and polar science. We present the different datasets along with a scheme to make machine learning challenges around the three datasets findable, accessible, interoperable, and reusable (FAIR). Furthermore, we present an approach that generalizes to future machine learning challenges, enabling the possibility of large, more compute-intensive challenges that can ultimately lead to scientific discovery.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Contrôle bibliographique ouvert
La source scientifique ouverte est momentanément indisponible.
Sujets associés
Anomaly Detection Techniques and Applications