{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T01:26:01Z","timestamp":1792891561514,"version":"4.5.0"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"8-10","license":[{"start":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T00:00:00Z","timestamp":1526947200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s10994-018-5715-3","type":"journal-article","created":{"date-parts":[[2018,5,22]],"date-time":"2018-05-22T15:57:46Z","timestamp":1527004666000},"page":"1561-1595","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Learning from binary labels with instance-dependent noise"],"prefix":"10.1007","volume":"107","author":[{"given":"Aditya Krishna","family":"Menon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brendan","family":"van Rooyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nagarajan","family":"Natarajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,5,22]]},"reference":[{"key":"5715_CR1","first-page":"1653","volume":"15","author":"S Agarwal","year":"2014","unstructured":"Agarwal, S. (2014). Surrogate regret bounds for bipartite ranking via strongly proper losses. Journal of Machine Learning Research, 15, 1653\u20131674.","journal-title":"Journal of Machine Learning Research"},{"key":"5715_CR2","doi-asserted-by":"crossref","unstructured":"Agarwal, S., & Niyogi, P. (2005). Stability and generalization of bipartite ranking algorithms. In Conference on learning theory (COLT), Springer (pp. 32\u201347).","DOI":"10.1007\/11503415_3"},{"issue":"4","key":"5715_CR3","first-page":"343","volume":"2","author":"D Angluin","year":"1988","unstructured":"Angluin, D., & Laird, P. (1988). Learning from noisy examples. Machine Learning, 2(4), 343\u2013370.","journal-title":"Machine Learning"},{"key":"5715_CR4","doi-asserted-by":"crossref","unstructured":"Awasthi, P., Balcan, M. F., & Long, P. M. (2014). The power of localization for efficiently learning linear separators with noise. In Symposium on the theory of computing (STOC) (pp. 449\u2013458).","DOI":"10.1145\/2591796.2591839"},{"key":"5715_CR5","first-page":"167","volume":"40","author":"P Awasthi","year":"2015","unstructured":"Awasthi, P., Balcan, M. F., Haghtalab, N., & Urner, R. (2015). Efficient learning of linear separators under bounded noise. Conference on Learning Theory (COLT), 40, 167\u2013190.","journal-title":"Conference on Learning Theory (COLT)"},{"key":"5715_CR6","unstructured":"Awasthi, P., Balcan, M., Haghtalab, N., & Zhang, H. (2016). Learning and 1-bit compressed sensing under asymmetric noise. In Conference on learning theory (COLT) (pp. 152\u2013192)."},{"issue":"6","key":"5715_CR7","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1145\/3006384","volume":"63","author":"P Awasthi","year":"2017","unstructured":"Awasthi, P., Balcan, M., & Long, P. M. (2017). The power of localization for efficiently learning linear separators with noise. Journal of the ACM, 63(6), 50.","journal-title":"Journal of the ACM"},{"issue":"4","key":"5715_CR8","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1214\/aoms\/1177728423","volume":"26","author":"M Ayer","year":"1955","unstructured":"Ayer, M., Brunk, H. D., Ewing, G. M., Reid, W. T., & Silverman, E. (1955). An empirical distribution function for sampling with incomplete information. The Annals of Mathematical Statistics, 26(4), 641\u2013647.","journal-title":"The Annals of Mathematical Statistics"},{"issue":"473","key":"5715_CR9","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1198\/016214505000000907","volume":"101","author":"PL Bartlett","year":"2006","unstructured":"Bartlett, P. L., Jordan, M. I., & McAuliffe, J. D. (2006). Convexity, classification, and risk bounds. Journal of the American Statistical Association, 101(473), 138\u2013156.","journal-title":"Journal of the American Statistical Association"},{"key":"5715_CR10","unstructured":"Bhatia, K., Jain, P., & Kar, P. (2015). Robust regression via hard thresholding. In Advances in neural information processing systems (NIPS) (pp. 721\u2013729)."},{"key":"5715_CR11","doi-asserted-by":"crossref","unstructured":"Blum, A., & Mitchell, T. (1998). Combining labeled and unlabeled data with co-training. In Conference on learning theory (COLT) (pp. 92\u2013100).","DOI":"10.1145\/279943.279962"},{"key":"5715_CR12","doi-asserted-by":"crossref","unstructured":"Blum, A., Frieze, A., Kannan, R., & Vempala, S.(1996). A polynomial-time algorithm for learning noisy linear threshold functions. In Foundations of computer science (FOCS) (pp. 330\u2013338).","DOI":"10.1109\/SFCS.1996.548492"},{"key":"5715_CR13","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.neucom.2015.12.106","volume":"192","author":"J Bootkrajang","year":"2016","unstructured":"Bootkrajang, J. (2016). A generalised label noise model for classification in the presence of annotation errors. Neurocomputing, 192, 61\u201371.","journal-title":"Neurocomputing"},{"issue":"11","key":"5715_CR14","doi-asserted-by":"publisher","first-page":"3641","DOI":"10.1016\/j.patcog.2014.05.007","volume":"47","author":"J Bootkrajang","year":"2014","unstructured":"Bootkrajang, J., & Kab\u00e1n, A. (2014). Learning kernel logistic regression in the presence of class label noise. Pattern Recognition, 47(11), 3641\u20133655.","journal-title":"Pattern Recognition"},{"key":"5715_CR15","doi-asserted-by":"crossref","unstructured":"Bylander, T. (1994). Learning linear threshold functions in the presence of classification noise. In Conference on learning theory (COLT) (pp. 340\u2013347).","DOI":"10.1145\/180139.181176"},{"key":"5715_CR16","doi-asserted-by":"crossref","unstructured":"Bylander, T. (1997). Learning probabilistically consistent linear threshold functions. In Conference on learning theory (COLT) (pp. 62\u201371).","DOI":"10.1145\/267460.267479"},{"key":"5715_CR17","unstructured":"Bylander, T. (1998). Learning noisy linear threshold functions (unpublished manuscript). http:\/\/www.cs.utsa.edu\/~bylander\/pubs\/learning-noisy-ltfs.ps.gz ."},{"issue":"2","key":"5715_CR18","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1214\/009052607000000910","volume":"36","author":"S Cl\u00e9men\u00e7on","year":"2008","unstructured":"Cl\u00e9men\u00e7on, S., Lugosi, G., & Vayatis, N. (2008). Ranking and empirical minimization of U-statistics. The Annals of Statistics, 36(2), 844\u2013874.","journal-title":"The Annals of Statistics"},{"key":"5715_CR19","unstructured":"Decatur, S. E. (1997). PAC learning with constant-partition classification noise and applications to decision tree induction. In International conference on machine learning (ICML) (pp. 83\u201391)."},{"key":"5715_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0711-5","volume-title":"A probabilistic theory of pattern recognition","author":"L Devroye","year":"1996","unstructured":"Devroye, L., Gy\u00f6rfi, L., & Lugosi, G. (1996). A probabilistic theory of pattern recognition. Berlin: Springer."},{"key":"5715_CR21","doi-asserted-by":"crossref","unstructured":"Du, J., & Cai, Z. (2015). Modelling class noise with symmetric and asymmetric distributions. In Conference on artificial intelligence (AAAI) (pp. 2589\u20132595).","DOI":"10.1609\/aaai.v29i1.9612"},{"key":"5715_CR22","doi-asserted-by":"crossref","unstructured":"Elkan, C., & Noto, K. (2008). Learning classifiers from only positive and unlabeled data. In International conference on knowledge discovery and data mining (KDD) (pp. 213\u2013220).","DOI":"10.1145\/1401890.1401920"},{"key":"5715_CR23","unstructured":"Fr\u00e9nay, B., & Kab\u00e1n, A. (2014). A comprehensive introduction to label noise. In European symposium on artificial neural networks (ESANN) (pp. 667\u2014676)."},{"issue":"5","key":"5715_CR24","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","volume":"25","author":"B Fr\u00e9nay","year":"2014","unstructured":"Fr\u00e9nay, B., & Verleysen, M. (2014). Classification in the presence of label noise: A survey. IEEE Transactions on Neural Networks and Learning Systems, 25(5), 845\u2013869.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"5715_CR25","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. (2015). Making risk minimization tolerant to label noise. Neurocomputing, 160, 93\u2013107.","journal-title":"Neurocomputing"},{"key":"5715_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"5715_CR27","unstructured":"Jain, S., White, M., & Radivojac, P. (2016). Estimating the class prior and posterior from noisy positives and unlabeled data. In Advances in neural information processing systems (NIPS) (pp. 2685\u20132693)."},{"key":"5715_CR28","unstructured":"Kakade, S., Kanade, V., Shamir, O., & Kalai, A.(2011). Efficient learning of generalized linear and single index models with isotonic regression. In Advances in neural information processing systems (NIPS) (pp. 927\u2013935)."},{"key":"5715_CR29","unstructured":"Kalai, A., & Sastry, R. (2009). The Isotron algorithm: High-dimensional isotonic regression. In Conference on learning theory (COLT)."},{"key":"5715_CR30","doi-asserted-by":"crossref","unstructured":"Kalai, A., Klivans, A., Mansour, Y., & Servedio, R. (2005). Agnostically learning halfspaces. In Foundations of computer systems (FOCS) (pp. 11\u201320).","DOI":"10.1109\/SFCS.2005.13"},{"key":"5715_CR31","unstructured":"Koyejo, O. O., Natarajan, N., Ravikumar, P. K., & Dhillon, I. S. (2014). Consistent binary classification with generalized performance metrics. In Advances in neural information processing systems (NIPS) (pp. 2744\u20132752)."},{"key":"5715_CR32","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (NIPS) (pp. 1106\u20131114)."},{"key":"5715_CR33","doi-asserted-by":"crossref","unstructured":"Le, Q. V., Smola, A. J., & Canu, S. (2005). Heteroscedastic gaussian process regression. In International conference on machine learning (ICML) (pp. 489\u2013496).","DOI":"10.1145\/1102351.1102413"},{"key":"5715_CR34","unstructured":"Ling, C. X., & Li, C. (1998). Data mining for direct marketing: Problems and solutions. In Knowledge discovery and data mining (KDD) (pp. 73\u201379)."},{"key":"5715_CR35","first-page":"447","volume":"2001","author":"T Liu","year":"2015","unstructured":"Liu, T., & Tao, D. (2015). Classification with noisy labels by importance reweighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 447\u2013461.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"5715_CR36","doi-asserted-by":"crossref","unstructured":"Long, P., & Servedio, R. (2008). Random classification noise defeats all convex potential boosters. In International conference on machine learning (ICML) (pp. 608\u2013615).","DOI":"10.1145\/1390156.1390233"},{"issue":"3","key":"5715_CR37","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1109\/TSMCB.2012.2223460","volume":"43","author":"N Manwani","year":"2013","unstructured":"Manwani, N., & Sastry, P. S. (2013). Noise tolerance under risk minimization. IEEE Transactions on Cybernetics, 43(3), 1146\u20131151.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"5","key":"5715_CR38","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1214\/009053606000000786","volume":"34","author":"P Massart","year":"2006","unstructured":"Massart, P., & N\u00e9d\u00e9lec, E. (2006). Risk bounds for statistical learning. The Annals of Statistics, 34(5), 2326\u20132366.","journal-title":"The Annals of Statistics"},{"key":"5715_CR39","unstructured":"Menon, A. K., van Rooyen, B., Ong, C. S., & Williamson, B. (2015). Learning from corrupted binary labels via class-probability estimation. In International conference on machine learning (ICML) (pp. 125\u2013134)."},{"key":"5715_CR40","unstructured":"Narasimhan, H., Vaish, R., & Agarwal, S. (2014). On the statistical consistency of plug-in classifiers for non-decomposable performance measures. In Advances in neural information processing systems (NIPS) (pp. 1493\u20131501)."},{"key":"5715_CR41","unstructured":"Natarajan, N., Dhillon, I. S., Ravikumar, P. D., & Tewari, A. (2013). Learning with noisy labels. In Advances in neural information processing systems (NIPS) (pp. 1196\u20131204)."},{"issue":"4","key":"5715_CR42","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1109\/TIT.2013.2240435","volume":"59","author":"NH Nguyen","year":"2013","unstructured":"Nguyen, N. H., & Tran, T. D. (2013). Exact recoverability from dense corrupted observations via $$\\ell _1$$ \u2113 1 -minimization. IEEE Transactions on Information Theory, 59(4), 2017\u20132035.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5715_CR43","unstructured":"Patrini, G., Nielsen, F., Nock, R., & Carioni, M.(2016). Loss factorization, weakly supervised learning and label noise robustness. In International conference on machine learning (ICML) (pp. 708\u2013717)."},{"key":"5715_CR44","doi-asserted-by":"crossref","unstructured":"Patrini, G., Rozza, A., Menon, A., Nock, R., & Qu, L. (2017). Making deep neural networks robust to label noise: A loss correction approach. In Computer vision and pattern recognition (CVPR) (pp. 2233\u20132241).","DOI":"10.1109\/CVPR.2017.240"},{"key":"5715_CR45","unstructured":"Plessis, M. C., Niu, G., Sugiyama, M. (2015). Convex formulation for learning from positive and unlabeled data. In International conference on machine learning (ICML) (pp. 1386\u20131394)."},{"key":"5715_CR46","doi-asserted-by":"crossref","unstructured":"Ralaivola, L., Denis, F., & Magnan, C. N.(2006). CN = CPCN. In International conference on machine learning (ICML) (pp. 721\u2013728).","DOI":"10.1145\/1143844.1143935"},{"key":"5715_CR47","unstructured":"Reed, S. E., Lee, H., Anguelov, D., Szegedy, C., Erhan, D., & Rabinovich, A. (2014). Training deep neural networks on noisy labels with bootstrapping. CoRR abs\/1412.6596."},{"key":"5715_CR48","doi-asserted-by":"crossref","unstructured":"Reid, M. D., & Williamson, R. C.(2009). Surrogate regret bounds for proper losses. In International conference on machine learning (ICML) (pp. 897\u2013904).","DOI":"10.1145\/1553374.1553489"},{"key":"5715_CR49","unstructured":"van Rooyen, B., Menon, A. K., & Williamson, R. C. (2015). Learning with symmetric label noise: the importance of being unhinged. In Advances in neural information processing systems (NIPS) (pp. 10\u201318)."},{"key":"5715_CR50","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","volume-title":"Learning with kernels","author":"B Sch\u00f6lkopf","year":"2001","unstructured":"Sch\u00f6lkopf, B., & Smola, A. J. (2001). Learning with kernels. Cambridge: MIT Press."},{"key":"5715_CR51","unstructured":"Scott, C., Blanchard, G., & Handy, G. (2013). Classification with asymmetric label noise: Consistency and maximal denoising. In Conference on learning theory (COLT) (pp. 489\u2013511)."},{"key":"5715_CR52","doi-asserted-by":"crossref","unstructured":"Servedio, R. (1999). On PAC learning using winnow, perceptron, and a perceptron-like algorithm. In Conference on learning theory (COLT) (pp. 296\u2013307).","DOI":"10.1145\/307400.307474"},{"key":"5715_CR53","unstructured":"Shalizi, C. R. (2017). Advanced data analysis from an elementary point of view (unpublished book draft). http:\/\/www.stat.cmu.edu\/~cshalizi\/ADAfaEPoV\/ADAfaEPoV.pdf ."},{"key":"5715_CR54","doi-asserted-by":"crossref","unstructured":"Steinwart, I., & Scovel, C. (2005). Fast rates for support vector machines. In Conference on learning theory (COLT) (pp. 279\u2013294).","DOI":"10.1007\/11503415_19"},{"key":"5715_CR55","doi-asserted-by":"crossref","unstructured":"Stempfel, G., & Ralaivola, L. (2007). Learning kernel perceptrons on noisy data using random projections. In Algorithmic learning theory (ALT) (pp. 328\u2013342).","DOI":"10.1007\/978-3-540-75225-7_27"},{"key":"5715_CR56","doi-asserted-by":"crossref","unstructured":"Stempfel, G., & Ralaivola, L. (2009). Learning SVMs from sloppily labeled data. In International conference on artificial neural networks (ICANN) (pp. 884\u2013893).","DOI":"10.1007\/978-3-642-04274-4_91"},{"issue":"7","key":"5715_CR57","doi-asserted-by":"publisher","first-page":"3540","DOI":"10.1109\/TIT.2010.2048473","volume":"56","author":"J Wright","year":"2010","unstructured":"Wright, J., & Ma, Y. (2010). Dense error correction via $$\\ell _1$$ \u2113 1 -minimization. IEEE Transactions on Information Theory, 56(7), 3540\u20133560.","journal-title":"IEEE Transactions on Information Theory"},{"key":"5715_CR58","unstructured":"Xiao, T., Xia, T., Yang, Y., Huang, C., & Wang, X.(2015). Learning from massive noisy labeled data for image classification. In IEEE conference on computer vision and pattern recognition (CVPR) (pp. 2691\u20132699)."},{"issue":"1","key":"5715_CR59","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1214\/aos\/1079120130","volume":"32","author":"T Zhang","year":"2004","unstructured":"Zhang, T. (2004). Statistical behavior and consistency of classification methods based on convex risk minimization. Annals of Statistics, 32(1), 56\u201385.","journal-title":"Annals of Statistics"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-018-5715-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5715-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5715-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T22:43:49Z","timestamp":1720305829000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-018-5715-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,22]]},"references-count":59,"journal-issue":{"issue":"8-10","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["5715"],"URL":"https:\/\/doi.org\/10.1007\/s10994-018-5715-3","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,22]]},"assertion":[{"value":"28 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}