{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:03:24Z","timestamp":1757617404713,"version":"3.44.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"7-8","license":[{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"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":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s13042-025-02537-9","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:08:59Z","timestamp":1737526139000},"page":"4711-4726","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking learning difficulty and uncertainty of samples with a target perturbation-aware bias-variance decomposition"],"prefix":"10.1007","volume":"16","author":[{"given":"Rujing","family":"Yao","sequence":"first","affiliation":[]},{"given":"Ou","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Fang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"issue":"8","key":"2537_CR1","doi-asserted-by":"publisher","first-page":"3784","DOI":"10.1109\/TNNLS.2017.2736643","volume":"29","author":"A Dal Pozzolo","year":"2018","unstructured":"Dal Pozzolo A, Boracchi G, Caelen O, Alippi C, Bontempi G (2018) Credit card fraud detection: a realistic modeling and a novel learning strategy. IEEE Trans Neural Netw Learn Syst 29(8):3784\u20133797","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"2537_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3415156","volume":"15","author":"MJ Siers","year":"2021","unstructured":"Siers MJ, Islam MZ (2021) Class imbalance and cost-sensitive decision trees: a unified survey based on a core similarity. ACM Trans Knowl Discov Data 15(1):1\u201331","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2537_CR3","doi-asserted-by":"crossref","unstructured":"Li B, Liu Y, Wang X (2019) Gradient harmonized single-stage detector. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), pp 8577\u20138584","DOI":"10.1609\/aaai.v33i01.33018577"},{"issue":"7","key":"2537_CR4","doi-asserted-by":"publisher","first-page":"2940","DOI":"10.1109\/TNNLS.2020.3047335","volume":"33","author":"KRM Fernando","year":"2022","unstructured":"Fernando KRM, Tsokos CP (2022) Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks. IEEE Trans Neural Netw Learn Syst 33(7):2940\u20132951","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2537_CR5","unstructured":"Kumar M, Packer B, Koller D (2010) Self-paced learning for latent variable models. In: Annual conference on neural information processing systems (NeurIPS), pp 1189\u20131197"},{"issue":"9","key":"2537_CR6","doi-asserted-by":"crossref","first-page":"4555","DOI":"10.1109\/TPAMI.2021.3072422","volume":"44","author":"X Wang","year":"2022","unstructured":"Wang X, Chen Y, Zhu W (2022) A survey on curriculum learning. IEEE Trans Pattern Anal Mach Intell 44(9):4555\u20134576","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"2537_CR7","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1109\/TCYB.2020.2990908","volume":"52","author":"G Lyu","year":"2022","unstructured":"Lyu G, Feng S, Wang T, Lang C (2022) A self-paced regularization framework for partial-label learning. IEEE Trans Cybern 52(2):899\u2013911","journal-title":"IEEE Trans Cybern"},{"key":"2537_CR8","unstructured":"Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: International conference on machine learning (ICML), pp 148\u2013156"},{"key":"2537_CR9","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 2999\u20133007","DOI":"10.1109\/ICCV.2017.324"},{"key":"2537_CR10","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar M, Pourpanah F, Hussain S, Rezazadegan D, Liu L, Ghavamzadeh M, Fieguth P, Cao X, Khosravi A, Acharya UR, Makarenkov V, Nahavandi S (2021) A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Inf Fus 76:243\u2013297","journal-title":"Inf Fus"},{"key":"2537_CR11","doi-asserted-by":"crossref","unstructured":"Qin JC, Jiang R, Mo H, Dong D (2024) A data-driven mixed integer programming approach for joint chance-constrained optimal power flow under uncertainty. Int J Mach Learn Cybern 1\u201317","DOI":"10.1007\/s13042-024-02325-x"},{"key":"2537_CR12","doi-asserted-by":"crossref","unstructured":"Yang X, Luo Y, Xiu Y, Wang W, Xu H, Fan Z (2023) D-if: uncertainty-aware human digitization via implicit distribution field. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 9122\u20139132","DOI":"10.1109\/ICCV51070.2023.00837"},{"key":"2537_CR13","unstructured":"Gawlikowski J, Tassi CRN, Ali M, Lee J, Humt M, Feng J, Kruspe A, Triebel R, Jung P, Roscher R, Shahzad M, Yang W, Bamler R, Zhu XX (2021) A survey of uncertainty in deep neural networks. arXiv:2107.03342"},{"issue":"2","key":"2537_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3429447","volume":"15","author":"M Almeida","year":"2021","unstructured":"Almeida M, Zhuang Y, Ding W, Crouter SE, Chen P (2021) Mitigating class-boundary label uncertainty to reduce both model bias and variance. ACM Trans Knowl Discov Data 15(2):1\u201318","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2537_CR15","doi-asserted-by":"crossref","unstructured":"Aguilar E, Nagarajan B, Khatun R, Bola\u00f1os M, Radeva P (2020) Uncertainty modeling and deep learning applied to food image analysis. In: Proceedings of the 13th international joint conference on biomedical engineering systems and technologies (BIOSTEC), pp 9\u201316","DOI":"10.5220\/0009429400090016"},{"issue":"9","key":"2537_CR16","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1038\/nmat2825","volume":"9","author":"T Sakanoue","year":"2010","unstructured":"Sakanoue T, Sirringhaus H (2010) Band-like temperature dependence of mobility in a solution-processed organic semiconductor. Nat Mater 9(9):736\u2013740","journal-title":"Nat Mater"},{"issue":"3","key":"2537_CR17","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1109\/TCYB.2019.2957101","volume":"51","author":"K Wang","year":"2021","unstructured":"Wang K, Wang Y, Zhao Q, Meng D, Liao X, Xu Z (2021) Splboost: an improved robust boosting algorithm based on self-paced learning. IEEE Trans Cybern 51(3):1556\u20131570","journal-title":"IEEE Trans Cybern"},{"key":"2537_CR18","doi-asserted-by":"crossref","unstructured":"Wang Z, Shang J, Liu L, Lu L, Liu J, Han J (2019) Crossweigh: training named entity tagger from imperfect annotations. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP), pp 5153\u20135162","DOI":"10.18653\/v1\/D19-1519"},{"key":"2537_CR19","doi-asserted-by":"crossref","unstructured":"Huang J, Qu, L., Jia, R., Zhao, B (2019) O2u-net: a simple noisy label detection approach for deep neural networks. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 3325\u20133333","DOI":"10.1109\/ICCV.2019.00342"},{"key":"2537_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107585","volume":"110","author":"C Santiago","year":"2021","unstructured":"Santiago C, Barata C, Sasdelli M, Carneiro G, Nascimento JC (2021) Low: training deep neural networks by learning optimal sample weights. Pattern Recognit 110:107585","journal-title":"Pattern Recognit"},{"key":"2537_CR21","doi-asserted-by":"crossref","unstructured":"Xiao Y, Wang WY (2019) Quantifying uncertainties in natural language processing tasks. In: Proceedings of the AAAI conference on artificial intelligence (AAAI), pp 7322\u20137329","DOI":"10.1609\/aaai.v33i01.33017322"},{"key":"2537_CR22","unstructured":"Zhang J, Zhu J, Niu G, Han B, Sugiyama M, Kankanhalli M (2021) Geometry-aware instance-reweighted adversarial training. In: International conference on learning representations (ICLR)"},{"key":"2537_CR23","unstructured":"Baldock R, Maennel H, Neyshabur B (2021) Deep learning through the lens of example difficulty. In: Annual conference on neural information processing systems (NeurIPS), pp 10876\u201310889"},{"key":"2537_CR24","unstructured":"Zhu W, Wu O, Su F, Deng Y (2022) Exploring the learning difficulty of data theory and measure. arXiv:2205.07427"},{"key":"2537_CR25","doi-asserted-by":"crossref","unstructured":"Zhou X, Wu O, Zhu W, Liang Z (2022) Understanding difficulty-based sample weighting with a universal difficulty measure. In: Machine learning and knowledge discovery in databases-European conference (ECML-PKDD), pp 68\u201384","DOI":"10.1007\/978-3-031-26409-2_5"},{"issue":"5","key":"2537_CR26","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1109\/TCYB.2014.2344674","volume":"45","author":"J Zhang","year":"2015","unstructured":"Zhang J, Wu X, Shengs VS (2015) Active learning with imbalanced multiple noisy labeling. IEEE Trans Cybern 45(5):1095\u20131107","journal-title":"IEEE Trans Cybern"},{"key":"2537_CR27","unstructured":"Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision? In: Annual conference on neural information processing systems (NeurIPS), pp 5574\u20135584"},{"issue":"6","key":"2537_CR28","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.1109\/TCYB.2018.2821679","volume":"49","author":"TT Nguyen","year":"2019","unstructured":"Nguyen TT, Pham XC, Liew AW-C, Pedrycz W (2019) Aggregation of classifiers: a justifiable information granularity approach. IEEE Trans Cybern 49(6):2168\u20132177","journal-title":"IEEE Trans Cybern"},{"key":"2537_CR29","unstructured":"Yu Y, Yang Z, Dobriban E, Steinhardt J, Ma Y (2021) Understanding generalization in adversarial training via the bias-variance decomposition. arXiv:2103.09947"},{"key":"2537_CR30","unstructured":"Zhou H, Song L, Chen J, Zhou Y, Wang G, Yuan J, Zhang Q (2021) Rethinking soft labels for knowledge distillation: a bias-variance tradeoff perspective. In: International conference on learning representations (ICLR)"},{"key":"2537_CR31","unstructured":"Yang Z, Yu Y, You C, Steinhardt J, Ma Y (2020) Rethinking bias-variance trade-off for generalization of neural networks. In: International conference on machine learning (ICML), pp 10767\u201310777"},{"key":"2537_CR32","unstructured":"Reed S, Lee H, Anguelov D, Szegedy C, Erhan D, Rabinovich A (2015) Training deep neural networks on noisy labels with bootstrapping. In: International conference on learning representations (ICLR)"},{"key":"2537_CR33","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"2537_CR34","doi-asserted-by":"publisher","first-page":"5984","DOI":"10.1109\/TIP.2021.3089942","volume":"30","author":"C-B Zhang","year":"2021","unstructured":"Zhang C-B, Jiang P-T, Hou Q, Wei Y, Han Q, Li Z, Cheng M-M (2021) Delving deep into label smoothing. IEEE Trans Image Process 30:5984\u20135996","journal-title":"IEEE Trans Image Process"},{"key":"2537_CR35","doi-asserted-by":"crossref","unstructured":"Nair T, Precup D, Arnold DL, Arbel T (2018) Exploring uncertainty measures in deep networks for multiple sclerosis lesion detection and segmentation. In: International conference on medical image computing and computer assisted intervention (MICCAI), pp 655\u2013663","DOI":"10.1007\/978-3-030-00928-1_74"},{"key":"2537_CR36","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. In: International conference on machine learning (ICML), pp 1050\u20131059"},{"issue":"1","key":"2537_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-17876-z","volume":"7","author":"C Leibig","year":"2017","unstructured":"Leibig C, Allken V, Ayhan MS, Berens P, Wahl S (2017) Leveraging uncertainty information from deep neural networks for disease detection. Sci Rep 7(1):1\u201314","journal-title":"Sci Rep"},{"key":"2537_CR38","unstructured":"Bhatia K, Jain P, Kamalaruban P, Kar P (2017) Consistent robust regression. In: Annual conference on neural information processing systems (NeurIPS), pp 2110\u20132119"},{"key":"2537_CR39","doi-asserted-by":"crossref","unstructured":"Li Z, Zhang T, Shao W, Chen S, Zhang D (2021) Sign-aware perturbations regression. In: Proceedings of the 2021 SIAM international conference on data mining (SDM), pp 396\u2013404","DOI":"10.1137\/1.9781611976700.45"},{"key":"2537_CR40","unstructured":"Dalalyan A, Chen Y (2012) Fused sparsity and robust estimation for linear models with unknown variance. In: Annual conference on neural information processing systems (NeurIPS), pp 1268\u20131276"},{"issue":"4","key":"2537_CR41","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1109\/TIT.2013.2240435","volume":"59","author":"NH Nguyen","year":"2013","unstructured":"Nguyen NH, Tran TD (2013) Exact recoverability from dense corrupted observations via l1-minimization. IEEE Trans Inf Theory 59(4):2017\u20132035","journal-title":"IEEE Trans Inf Theory"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02537-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02537-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02537-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T03:45:20Z","timestamp":1757130320000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02537-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,22]]},"references-count":41,"journal-issue":{"issue":"7-8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2537"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02537-9","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,1,22]]},"assertion":[{"value":"3 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}