{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:56:21Z","timestamp":1760576181766,"version":"build-2065373602"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"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":[[2025,10]]},"DOI":"10.1007\/s13042-025-02681-2","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T05:14:05Z","timestamp":1748582045000},"page":"7689-7706","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FMW-Net: a first-order meta-weight-net approach for sample weighting"],"prefix":"10.1007","volume":"16","author":[{"given":"Yubo","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jun","family":"Shu","sequence":"additional","affiliation":[]},{"given":"Junmin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Deyu","family":"Meng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"2681_CR1","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"2681_CR2","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"2681_CR3","unstructured":"Ren M, Zeng W, Yang B, Urtasun R (2018) Learning to reweight examples for robust deep learning. In: International conference on machine learning, pp. 4334\u20134343. PMLR"},{"key":"2681_CR4","unstructured":"Shu J, Xie Q, Yi L, Zhao Q, Zhou S, Xu Z, Meng D (2019) Meta-weight-net: learning an explicit mapping for sample weighting. Adv Neural Inform Process Syst 32"},{"issue":"3","key":"2681_CR5","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64(3):107\u2013115","journal-title":"Commun ACM"},{"issue":"9","key":"2681_CR6","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2681_CR7","first-page":"26271","volume":"36","author":"S Choe","year":"2024","unstructured":"Choe S, Mehta SV, Ahn H, Neiswanger W, Xie P, Strubell E, Xing E (2024) Making scalable meta learning practical. Adv Neural Inf Process Syst 36:26271\u201326290","journal-title":"Adv Neural Inf Process Syst"},{"key":"2681_CR8","doi-asserted-by":"crossref","unstructured":"Wang S, Tan Z, Guo R, Li J (2023) Noise-robust fine-tuning of pretrained language models via external guidance. arXiv preprint arXiv:2311.01108","DOI":"10.18653\/v1\/2023.findings-emnlp.834"},{"key":"2681_CR9","first-page":"82","volume":"14","author":"W Bi","year":"2014","unstructured":"Bi W, Wang L, Kwok JT, Tu Z (2014) Learning to predict from crowdsourced data. UAI 14:82\u201391","journal-title":"UAI"},{"key":"2681_CR10","doi-asserted-by":"crossref","unstructured":"Zhuang B, Liu L, Li Y, Shen C, Reid I (2017) Attend in groups: a weakly-supervised deep learning framework for learning from web data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1878\u20131887","DOI":"10.1109\/CVPR.2017.311"},{"key":"2681_CR11","first-page":"3","volume":"1","author":"J Liang","year":"2016","unstructured":"Liang J, Jiang L, Meng D, Hauptmann AG (2016) Learning to detect concepts from webly-labeled video data. In: IJCAI 1:3\u20131","journal-title":"In: IJCAI"},{"key":"2681_CR12","unstructured":"Li W, Wang L, Li W, Agustsson E, Van Gool L (2017) Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862"},{"key":"2681_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2681_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.12.003","volume":"90","author":"S Fotouhi","year":"2019","unstructured":"Fotouhi S, Asadi S, Kattan MW (2019) A comprehensive data level analysis for cancer diagnosis on imbalanced data. J Biomed Inform 90:103089","journal-title":"J Biomed Inform"},{"issue":"2","key":"2681_CR15","doi-asserted-by":"publisher","first-page":"224","DOI":"10.7763\/IJMLC.2013.V3.307","volume":"3","author":"MM Rahman","year":"2013","unstructured":"Rahman MM, Davis DN (2013) Addressing the class imbalance problem in medical datasets. Int J Mach Learn Comput 3(2):224","journal-title":"Int J Mach Learn Comput"},{"issue":"4","key":"2681_CR16","doi-asserted-by":"publisher","first-page":"2518","DOI":"10.1109\/TII.2021.3100284","volume":"18","author":"S Fan","year":"2021","unstructured":"Fan S, Zhang X, Song Z (2021) Imbalanced sample selection with deep reinforcement learning for fault diagnosis. IEEE Trans Industr Inf 18(4):2518\u20132527","journal-title":"IEEE Trans Industr Inf"},{"key":"2681_CR17","doi-asserted-by":"crossref","unstructured":"Kong J, Kowalczyk W, Menzel S, B\u00e4ck T (2020) Improving imbalanced classification by anomaly detection. In: International conference on parallel problem solving from nature, pp. 512\u2013523. Springer","DOI":"10.1007\/978-3-030-58112-1_35"},{"key":"2681_CR18","unstructured":"Neyshabur B, Bhojanapalli S, McAllester D, Srebro N (2017) Exploring generalization in deep learning. Adv Neural Inform Process Syst 30"},{"key":"2681_CR19","unstructured":"Arpit D, Jastrzbski S, Ballas N, Krueger D, Bengio E, Kanwal MS, Maharaj T, Fischer A, Courville A, Bengio Y (2017) A closer look at memorization in deep networks. In: International conference on machine learning, pp. 233\u2013242. PMLR"},{"key":"2681_CR20","unstructured":"Novak R, Bahri Y, Abolafia DA, Pennington J, Sohl-Dickstein J (2018) Sensitivity and generalization in neural networks: an empirical study. arXiv preprint arXiv:1802.08760"},{"issue":"4","key":"2681_CR21","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1109\/TSMCC.2011.2161285","volume":"42","author":"M Galar","year":"2011","unstructured":"Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2011) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern Part C Appl Rev 42(4):463\u2013484","journal-title":"IEEE Trans Syst Man Cybern Part C Appl Rev"},{"key":"2681_CR22","doi-asserted-by":"publisher","first-page":"11521","DOI":"10.1109\/TPAMI.2023.3271451","volume":"45","author":"J Shu","year":"2023","unstructured":"Shu J, Yuan X, Meng D, Xu Z (2023) Cmw-net: learning a class-aware sample weighting mapping for robust deep learning. IEEE Trans Pattern Anal Mach Intell 45:11521\u201311539","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2681_CR23","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 international conference on computer Vision, pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"2681_CR24","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.ins.2017.05.043","volume":"414","author":"D Meng","year":"2017","unstructured":"Meng D, Zhao Q, Jiang L (2017) A theoretical understanding of self-paced learning. Inf Sci 414:319\u2013328","journal-title":"Inf Sci"},{"key":"2681_CR25","unstructured":"Zhang Z, Sabuncu M (2018) Generalized cross entropy loss for training deep neural networks with noisy labels. Adv Neural Inform Process Syst 31"},{"issue":"2","key":"2681_CR26","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1214\/aos\/1016218223","volume":"28","author":"J Friedman","year":"2000","unstructured":"Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann Stat 28(2):337\u2013407","journal-title":"Ann Stat"},{"key":"2681_CR27","doi-asserted-by":"crossref","unstructured":"Park S, Lim J, Jeon Y, Choi JY (2021) Influence-balanced loss for imbalanced visual classification. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 735\u2013744","DOI":"10.1109\/ICCV48922.2021.00077"},{"key":"2681_CR28","doi-asserted-by":"crossref","unstructured":"Zhang Z, Pfister T (2021) Learning fast sample re-weighting without reward data. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 725\u2013734","DOI":"10.1109\/ICCV48922.2021.00076"},{"key":"2681_CR29","doi-asserted-by":"crossref","unstructured":"Pan R, Zhang J, Pan X, Pi R, Wang X, Zhang T (2024) Scalebio: Scalable bilevel optimization for llm data reweighting. arXiv preprint arXiv:2406.19976","DOI":"10.18653\/v1\/2025.acl-long.1543"},{"key":"2681_CR30","unstructured":"Liu H, Simonyan K, Yang Y (2018) Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055"},{"issue":"12","key":"2681_CR31","doi-asserted-by":"publisher","first-page":"10045","DOI":"10.1109\/TPAMI.2021.3132674","volume":"44","author":"R Liu","year":"2021","unstructured":"Liu R, Gao J, Zhang J, Meng D, Lin Z (2021) Investigating bi-level optimization for learning and vision from a unified perspective: A survey and beyond. IEEE Trans Pattern Anal Mach Intell 44(12):10045\u201310067","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2681_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inform Process Syst 30"},{"key":"2681_CR33","doi-asserted-by":"crossref","unstructured":"Dempe S, Zemkoho A (2020) Bilevel optimization 161","DOI":"10.1007\/978-3-030-52119-6"},{"issue":"1","key":"2681_CR34","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s10107-009-0323-4","volume":"123","author":"N Dinh","year":"2010","unstructured":"Dinh N, Mordukhovich B, Nghia TT (2010) Subdifferentials of value functions and optimality conditions for dc and bilevel infinite and semi-infinite programs. Math Progr 123(1):101\u2013138","journal-title":"Math Progr"},{"key":"2681_CR35","first-page":"29630","volume":"34","author":"C Gong","year":"2021","unstructured":"Gong C, Liu X, Liu Q (2021) Automatic and harmless regularization with constrained and lexicographic optimization: a dynamic barrier approach. Adv Neural Inf Process Syst 34:29630\u201329642","journal-title":"Adv Neural Inf Process Syst"},{"key":"2681_CR36","first-page":"17248","volume":"35","author":"B Liu","year":"2022","unstructured":"Liu B, Ye M, Wright S, Stone P, Liu Q (2022) Bome! bilevel optimization made easy: a simple first-order approach. Adv Neural Inf Process Syst 35:17248\u201317262","journal-title":"Adv Neural Inf Process Syst"},{"key":"2681_CR37","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International conference on machine learning, pp. 1126\u20131135. PMLR"},{"key":"2681_CR38","unstructured":"Liu R, Liu X, Yuan X, Zeng S, Zhang J (2021) A value-function-based interior-point method for non-convex bi-level optimization. In: International conference on machine learning, pp. 6882\u20136892. PMLR"},{"key":"2681_CR39","unstructured":"Shen H, Chen T (2023) On penalty-based bilevel gradient descent method. In: International conference on machine learning, pp. 30992\u201331015. PMLR"},{"key":"2681_CR40","unstructured":"Krizhevsky A, Hinton G, et al (2009) Learning multiple layers of features from tiny images"},{"key":"2681_CR41","doi-asserted-by":"crossref","unstructured":"Cui Y, Jia M, Lin T-Y, Song Y, Belongie S (2019) Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9268\u20139277","DOI":"10.1109\/CVPR.2019.00949"},{"key":"2681_CR42","unstructured":"Jiang L, Zhou Z, Leung T, Li L-J, Fei-Fei L (2018) Mentornet: learning data-driven curriculum for very deep neural networks on corrupted labels. In: International conference on machine learning, pp. 2304\u20132313. PMLR"},{"key":"2681_CR43","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. IEEE","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2681_CR44","doi-asserted-by":"crossref","unstructured":"Bengio Y, Louradour J, Collobert R, Weston J (2009) Curriculum learning. In: Proceedings of the 26th annual international conference on machine learning, pp. 41\u201348","DOI":"10.1145\/1553374.1553380"},{"key":"2681_CR45","doi-asserted-by":"publisher","unstructured":"Saravia E, Liu H-CT, Huang Y-H, Wu J, Chen Y-S (2018) CARER: Contextualized affect representations for emotion recognition. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp. 3687\u20133697. Association for Computational Linguistics, Brussels, Belgium. https:\/\/doi.org\/10.18653\/v1\/D18-1404 . https:\/\/www.aclweb.org\/anthology\/D18-1404","DOI":"10.18653\/v1\/D18-1404"},{"key":"2681_CR46","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321\u2013357","journal-title":"J Artif Intell Res"},{"key":"2681_CR47","doi-asserted-by":"crossref","unstructured":"Dong Q, Gong S, Zhu X (2017) Class rectification hard mining for imbalanced deep learning. In: Proceedings of the IEEE international conference on computer vision, pp. 1851\u20131860","DOI":"10.1109\/ICCV.2017.205"},{"issue":"6","key":"2681_CR48","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TPAMI.2018.2832629","volume":"41","author":"Q Dong","year":"2018","unstructured":"Dong Q, Gong S, Zhu X (2018) Imbalanced deep learning by minority class incremental rectification. IEEE Trans Pattern Anal Mach Intell 41(6):1367\u20131381","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2681_CR49","doi-asserted-by":"crossref","unstructured":"Zadrozny B (2004) Learning and evaluating classifiers under sample selection bias. In: Proceedings of the twenty-first international conference on machine learning, p. 114","DOI":"10.1145\/1015330.1015425"},{"key":"2681_CR50","first-page":"973","volume":"17","author":"C Elkan","year":"2001","unstructured":"Elkan C (2001) The foundations of cost-sensitive learning. Int Joint Conf Artif Intell 17:973\u2013978 (Lawrence Erlbaum Associates Ltd)","journal-title":"Int Joint Conf Artif Intell"},{"issue":"8","key":"2681_CR51","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1109\/TNNLS.2017.2732482","volume":"29","author":"SH Khan","year":"2017","unstructured":"Khan SH, Hayat M, Bennamoun M, Sohel FA, Togneri R (2017) Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Trans. Neural Netw Learn Syst 29(8):3573\u20133587","journal-title":"IEEE Trans. Neural Netw Learn Syst"},{"key":"2681_CR52","unstructured":"Kumar M, Packer B, Koller D (2010) Self-paced learning for latent variable models. Adv Neural Inform Process Syst 23"},{"key":"2681_CR53","doi-asserted-by":"crossref","unstructured":"Jiang L, Meng D, Mitamura T, Hauptmann AG (2014) Easy samples first: Self-paced reranking for zero-example multimedia search. In: Proceedings of the 22nd ACM international conference on multimedia, pp. 547\u2013556","DOI":"10.1145\/2647868.2654918"},{"key":"2681_CR54","unstructured":"Jiang L, Meng D, Yu S-I, Lan Z, Shan S, Hauptmann A (2014) Self-paced learning with diversity. Adv Neural Inform Process Syst 27"},{"key":"2681_CR55","doi-asserted-by":"crossref","unstructured":"Jiang L, Meng D, Zhao Q, Shan S, Hauptmann A (2015) Self-paced curriculum learning. In: Proceedings of the AAAI conference on artificial intelligence, vol. 29","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"2681_CR56","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1023\/A:1023709501986","volume":"54","author":"F De La Torre","year":"2003","unstructured":"De La Torre F, Black MJ (2003) A framework for robust subspace learning. Int J Comput Vision 54:117\u2013142","journal-title":"Int J Comput Vision"},{"issue":"1","key":"2681_CR57","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","volume":"55","author":"Y Freund","year":"1997","unstructured":"Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119\u2013139","journal-title":"J Comput Syst Sci"},{"key":"2681_CR58","doi-asserted-by":"crossref","unstructured":"Malisiewicz T, Gupta A, Efros AA (2011) Ensemble of exemplar-svms for object detection and beyond. In: 2011 international conference on computer vision, pp. 89\u201396. IEEE","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"2681_CR59","unstructured":"Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning. In: International conference on learning representations"},{"key":"2681_CR60","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inform Process Syst 30"},{"key":"2681_CR61","unstructured":"Fan Y, Tian F, Qin T, Li X-Y, Liu T-Y (2018) Learning to teach. arXiv preprint arXiv:1805.03643"},{"key":"2681_CR62","unstructured":"Wu L, Tian F, Xia Y, Fan Y, Qin T, Jian-Huang L, Liu T-Y (2018) Learning to teach with dynamic loss functions. Adv Neural Inform Process Syst 31"},{"key":"2681_CR63","unstructured":"Grazzi R, Franceschi L, Pontil M, Salzo S (2020) On the iteration complexity of hypergradient computation. In: International conference on machine learning, pp. 3748\u20133758. PMLR"},{"key":"2681_CR64","unstructured":"Franceschi L, Donini M, Frasconi P, Pontil M (2017) Forward and reverse gradient-based hyperparameter optimization. In: International conference on machine learning, pp. 1165\u20131173. PMLR"},{"key":"2681_CR65","unstructured":"Franceschi L, Frasconi P, Salzo S, Grazzi R, Pontil M (2018) Bilevel programming for hyperparameter optimization and meta-learning. In: International conference on machine learning, pp. 1568\u20131577. PMLR"},{"key":"2681_CR66","unstructured":"Maclaurin D, Duvenaud D, Adams R (2015) Gradient-based hyperparameter optimization through reversible learning. In: International conference on machine learning, pp. 2113\u20132122. PMLR"},{"key":"2681_CR67","unstructured":"Shaban A, Cheng C-A, Hatch N, Boots B (2019) Truncated back-propagation for bilevel optimization. In: The 22nd international conference on artificial intelligence and statistics, pp. 1723\u20131732. PMLR"},{"key":"2681_CR68","unstructured":"Rajeswaran A, Finn C, Kakade SM, Levine S (2019) Meta-learning with implicit gradients. Adv Neural Inform Process Syst 32"},{"key":"2681_CR69","unstructured":"Clarke RM, Oldewage ET, Hern\u00e1ndez-Lobato JM (2021) Scalable one-pass optimisation of high-dimensional weight-update hyperparameters by implicit differentiation. arXiv preprint arXiv:2110.10461"},{"key":"2681_CR70","unstructured":"Lorraine J, Vicol P, Duvenaud D (2020) Optimizing millions of hyperparameters by implicit differentiation. In: International conference on artificial intelligence and statistics, pp. 1540\u20131552. PMLR"},{"key":"2681_CR71","first-page":"8662","volume":"34","author":"R Liu","year":"2021","unstructured":"Liu R, Liu Y, Zeng S, Zhang J (2021) Towards gradient-based bilevel optimization with non-convex followers and beyond. Adv Neural Inf Process Syst 34:8662\u20138675","journal-title":"Adv Neural Inf Process Syst"},{"issue":"12","key":"2681_CR72","doi-asserted-by":"publisher","first-page":"15930","DOI":"10.1109\/TPAMI.2023.3303227","volume":"45","author":"R Liu","year":"2023","unstructured":"Liu R, Liu X, Zeng S, Zhang J, Zhang Y (2023) Value-function-based sequential minimization for bi-level optimization. IEEE Trans Pattern Anal Mach Intell 45(12):15930\u201315948","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2681_CR73","unstructured":"Shu J, Yuan X, Meng D, Xu Z (2023) Dac-mr: Data augmentation consistency based meta-regularization for meta-learning. arXiv preprint arXiv:2305.07892"},{"issue":"153","key":"2681_CR74","first-page":"1","volume":"18","author":"AG Baydin","year":"2018","unstructured":"Baydin AG, Pearlmutter BA, Radul AA, Siskind JM (2018) Automatic differentiation in machine learning: a survey. J Mach Learn Res 18(153):1\u201343","journal-title":"J Mach Learn Res"},{"key":"2681_CR75","doi-asserted-by":"crossref","unstructured":"Griewank A, Walther A (2008) Evaluating derivatives: principles and techniques of algorithmic differentiation","DOI":"10.1137\/1.9780898717761"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02681-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02681-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02681-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T16:58:57Z","timestamp":1760547537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02681-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":75,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["2681"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02681-2","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"assertion":[{"value":"14 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 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 Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}