{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T13:20:23Z","timestamp":1770729623859,"version":"3.49.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T00:00:00Z","timestamp":1714003200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003500","name":"Universit\u00e0 degli Studi di Padova","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003500","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Optim Lett"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In many contexts, customized and weighted classification scores are designed in order to evaluate the goodness of the predictions carried out by neural networks. However, there exists a discrepancy between the maximization of such scores and the minimization of the loss function in the training phase. In this paper, we provide a complete theoretical setting that formalizes weighted classification metrics and then allows the construction of losses that drive the model to optimize these metrics of interest. After a detailed theoretical analysis, we show that our framework includes as particular instances well-established approaches such as classical cost-sensitive learning, weighted cross entropy loss functions and value-weighted skill scores.<\/jats:p>","DOI":"10.1007\/s11590-024-02112-1","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T12:01:39Z","timestamp":1714046499000},"page":"169-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metrics"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1087-7589","authenticated-orcid":false,"given":"Francesco","family":"Marchetti","sequence":"first","affiliation":[]},{"given":"Sabrina","family":"Guastavino","sequence":"additional","affiliation":[]},{"given":"Cristina","family":"Campi","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Benvenuto","sequence":"additional","affiliation":[]},{"given":"Michele","family":"Piana","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,25]]},"reference":[{"key":"2112_CR1","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s11063-018-09977-1","volume":"50","author":"YS Aurelio","year":"2019","unstructured":"Aurelio, Y.S., de Almeida, G.M., Castro, C.L., de P\u00e1dua\u00a0Braga, A.: Learning from imbalanced data sets with weighted cross-entropy function. Neural Process. Lett. 50, 1937\u20131949 (2019)","journal-title":"Neural Process. Lett."},{"key":"2112_CR2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003002314","volume-title":"Probability models in engineering and science, vol. 193 of Mechanical Engineering,","author":"H Benaroya","year":"2005","unstructured":"Benaroya, H., Han, S.M.: Probability models in engineering and science, vol. 193 of Mechanical Engineering,. CRC\/Taylor & Francis, Boca Raton, FL (2005)"},{"key":"2112_CR3","unstructured":"Elkan, C.: The foundations of cost-sensitive learning, in International joint conference on artificial intelligence, vol.\u00a017, Lawrence Erlbaum Associates Ltd, pp.\u00a0973\u2013978 (2001)"},{"key":"2112_CR4","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, A., Garc\u00eda, S., Galar, M., Prati, R.C., Krawczyk, B., Herrera, F., Fern\u00e1ndez, A., Garc\u00eda, S., Galar, M., Prati, R.C. et\u00a0al. (2018) Cost-sensitive learning, Learning from Imbalanced Data Sets, pp.\u00a063\u201378","DOI":"10.1007\/978-3-319-98074-4_4"},{"key":"2112_CR5","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1111\/j.2517-6161.1952.tb00104.x","volume":"14","author":"IJ Good","year":"1952","unstructured":"Good, I.J.: Rational decisions. J. Roy. Statist. Soc. Ser. B 14, 107\u2013114 (1952)","journal-title":"J. Roy. Statist. Soc. Ser. B"},{"key":"2112_CR6","volume-title":"Deep learning, Adaptive Computation and Machine Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning, Adaptive Computation and Machine Learning. MIT Press, Cambridge, MA (2016)"},{"key":"2112_CR7","doi-asserted-by":"publisher","first-page":"A105","DOI":"10.1051\/0004-6361\/202243617","volume":"662","author":"S Guastavino","year":"2022","unstructured":"Guastavino, S., Marchetti, F., Benvenuto, F., Campi, C., Piana, M.: Implementation paradigm for supervised flare forecasting studies: A deep learning application with video data. Astronomy & Astrophysics 662, A105 (2022)","journal-title":"Astronomy & Astrophysics"},{"key":"2112_CR8","doi-asserted-by":"crossref","unstructured":"Guastavino, S., Marchetti, F., Benvenuto, F., Campi, C., Piana, M.: Operational solar flare forecasting via video-based deep learning, Frontiers in Astronomy and Space Sciences, 9 (2023)","DOI":"10.3389\/fspas.2022.1039805"},{"key":"2112_CR9","unstructured":"Guastavino, S., Piana, M., Benvenuto, F.: Bad and good errors: value-weighted skill scores in deep ensemble learning, IEEE Transactions on Neural Networks and Learning Systems, (2022)"},{"key":"2112_CR10","doi-asserted-by":"publisher","first-page":"20049","DOI":"10.1038\/s41598-022-23306-6","volume":"12","author":"S Guastavino","year":"2022","unstructured":"Guastavino, S., Piana, M., Tizzi, M., Cassola, F., Iengo, A., Sacchetti, D., Solazzo, E., Benvenuto, F.: Prediction of severe thunderstorm events with ensemble deep learning and radar data. Scientific Reports 12, 20049 (2022)","journal-title":"Scientific Reports"},{"key":"2112_CR11","volume-title":"Digital Design and Computer Architecture, Second Edition","author":"D Harris","year":"2012","unstructured":"Harris, D., Harris, S.: Digital Design and Computer Architecture, Second Edition, 2nd edn. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2012)","edition":"2"},{"key":"2112_CR12","doi-asserted-by":"crossref","unstructured":"Hu, A., Shneider, C., Tiwari, A., Camporeale, E.: Probabilistic prediction of dst storms one-day-ahead using full-disk soho images, Space Weather, p.\u00a0e2022SW003064 (2022)","DOI":"10.1029\/2022SW003064"},{"key":"2112_CR13","unstructured":"Huang, C., Zhai, S., Talbott, W., Martin, M.B., Sun, S.-Y., Guestrin, C., Susskind, J.: Addressing the loss-metric mismatch with adaptive loss alignment, In: Chaudhuri, K., Salakhutdinov, R. (eds.), Proceedings of the 36th International Conference on Machine Learning, vol.\u00a097 of Proceedings of Machine Learning Research, PMLR, 09\u201315 Jun 2019, pp.\u00a02891\u20132900 (2019)"},{"key":"2112_CR14","first-page":"45","volume":"25","author":"K Janocha","year":"2016","unstructured":"Janocha, K., Czarnecki, W.M.: On loss functions for deep neural networks in classification. Schedae Informaticae 25, 45\u201359 (2016)","journal-title":"Schedae Informaticae"},{"key":"2112_CR15","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-86340-1_31","volume-title":"Artificial Neural Networks and Machine Learning - ICANN 2021","author":"Q Jodelet","year":"2021","unstructured":"Jodelet, Q., Liu, X., Murata, T.: Balanced softmax cross-entropy for incremental learning. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) Artificial Neural Networks and Machine Learning - ICANN 2021, pp. 385\u2013396. Springer International Publishing, Cham (2021)"},{"key":"2112_CR16","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","volume":"172","author":"DS Kermany","year":"2018","unstructured":"Kermany, D.S., Goldbaum, M., Cai, W., Valentim, C.C., Liang, H., Baxter, S.L., McKeown, A., Yang, G., Wu, X., Yan, F., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122\u20131131 (2018)","journal-title":"Cell"},{"key":"2112_CR17","unstructured":"Ko\u00e7o, S., Capponi, C.: On multi-class classification through the minimization of the confusion matrix norm, In: Ong, C.S., Ho, T.B. (eds.), Asian Conference on Machine Learning, ACML 2013, Canberra, ACT, Australia, November 13-15, 2013, vol.\u00a029 of JMLR Workshop and Conference Proceedings, JMLR.org, pp.\u00a0277\u2013292 (2013)"},{"key":"2112_CR18","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T-Y Lin","year":"2020","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 42, 318\u2013327 (2020)","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2112_CR19","unstructured":"Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks, In: Balcan, M., Weinberger, K.Q. (eds.), Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, vol.\u00a048 of JMLR Workshop and Conference Proceedings, JMLR.org, pp.\u00a0507\u2013516 (2016)"},{"key":"2112_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108913","volume":"132","author":"F Marchetti","year":"2022","unstructured":"Marchetti, F., Guastavino, S., Piana, M., Campi, C.: Score-oriented loss (sol) functions. Pattern Recognition 132, 108913 (2022)","journal-title":"Pattern Recognition"},{"key":"2112_CR21","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1017\/S1350482702003043","volume":"9","author":"KR Mylne","year":"2002","unstructured":"Mylne, K.R.: Decision-making from probability forecasts based on forecast value. Meteorological Applications 9, 307\u2013315 (2002)","journal-title":"Meteorological Applications"},{"key":"2112_CR22","unstructured":"Narasimhan, H., Kar, P., Jain, P.: Optimizing non-decomposable performance measures: A tale of two classes, In: Bach, F., Blei, D. (eds.), Proceedings of the 32nd International Conference on Machine Learning, vol.\u00a037 of Proceedings of Machine Learning Research, Lille, France, 07\u201309 Jul PMLR, pp.\u00a0199\u2013208 (2015)"},{"key":"2112_CR23","unstructured":"Narasimhan, H., Menon, A.K.: Training over-parameterized models with non-decomposable objectives, In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.), Advances in Neural Information Processing Systems, (2021)"},{"key":"2112_CR24","doi-asserted-by":"publisher","first-page":"523","DOI":"10.3390\/rs11050523","volume":"11","author":"C Pelletier","year":"2019","unstructured":"Pelletier, C., Webb, G.I., Petitjean, F.: Temporal convolutional neural network for the classification of satellite image time series. Remote. Sens. 11, 523 (2019)","journal-title":"Remote. Sens."},{"key":"2112_CR25","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I.D., Savarese, S.: Generalized intersection over union: A metric and a loss for bounding box regression, In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, Computer Vision Foundation \/ IEEE, pp.\u00a0658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2112_CR26","doi-asserted-by":"crossref","unstructured":"Singh, A., Pr\u00edncipe, J.C.: A loss function for classification based on a robust similarity metric, In: International Joint Conference on Neural Networks, IJCNN 2010, Barcelona, Spain, 18-23 July, 2010, IEEE, pp.\u00a01\u20136 (2010)","DOI":"10.1109\/IJCNN.2010.5596485"},{"key":"2112_CR27","doi-asserted-by":"crossref","unstructured":"Thai-Nghe, N., Gantner, Z., Schmidt-Thieme, L.:, Cost-sensitive learning methods for imbalanced data, In: The 2010 International joint conference on neural networks (IJCNN), IEEE, pp.\u00a01\u20138 (2010).","DOI":"10.1109\/IJCNN.2010.5596486"},{"key":"2112_CR28","doi-asserted-by":"crossref","unstructured":"Zadrozny, B., Langford, J., Abe, N.: Cost-sensitive learning by cost-proportionate example weighting, In: Third IEEE International Conference on Data Mining, pp.\u00a0435\u2013442 (2003)","DOI":"10.1109\/ICDM.2003.1250950"},{"key":"2112_CR29","unstructured":"Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels, In: Montr\u00e9al, Canada, Bengio, S., Wallach, H.M., 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, December 3-8, 2018, pp.\u00a08792\u20138802 (2018)"},{"key":"2112_CR30","doi-asserted-by":"publisher","first-page":"10888","DOI":"10.1109\/ACCESS.2019.2960065","volume":"8","author":"Q Zhu","year":"2020","unstructured":"Zhu, Q., Zhang, P., Wang, Z., Ye, X.: A new loss function for CNN classifier based on predefined evenly-distributed class centroids. IEEE Access 8, 10888\u201310895 (2020)","journal-title":"IEEE Access"}],"container-title":["Optimization Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11590-024-02112-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11590-024-02112-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11590-024-02112-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T10:02:17Z","timestamp":1736935337000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11590-024-02112-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,25]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["2112"],"URL":"https:\/\/doi.org\/10.1007\/s11590-024-02112-1","relation":{},"ISSN":["1862-4472","1862-4480"],"issn-type":[{"value":"1862-4472","type":"print"},{"value":"1862-4480","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,25]]},"assertion":[{"value":"22 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}