{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:25:24Z","timestamp":1740122724908,"version":"3.37.3"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T00:00:00Z","timestamp":1656892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T00:00:00Z","timestamp":1656892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"DOI":"10.1007\/s10489-022-03695-x","type":"journal-article","created":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T11:14:06Z","timestamp":1656933246000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HydaLearn"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1742-5561","authenticated-orcid":false,"given":"Sam","family":"Verboven","sequence":"first","affiliation":[]},{"given":"Muhammad Hafeez","family":"Chaudhary","sequence":"additional","affiliation":[]},{"given":"Jeroen","family":"Berrevoets","sequence":"additional","affiliation":[]},{"given":"Vincent","family":"Ginis","sequence":"additional","affiliation":[]},{"given":"Wouter","family":"Verbeke","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,4]]},"reference":[{"issue":"1","key":"3695_CR1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana R (1997) Multitask learning. Machine learning 28(1):41\u201375","journal-title":"Machine learning"},{"key":"3695_CR2","unstructured":"Du Y, Czarnecki W M, Jayakumar S M, Pascanu R, Lakshminarayanan B (2018) Adapting auxiliary losses using gradient similarity. arXiv preprint arXiv:1812.02224"},{"key":"3695_CR3","unstructured":"Sener O, Koltun V (2018) Multi-task learning as multi-objective optimization. In: Advances in Neural Information Processing Systems, pp 527\u2013538"},{"key":"3695_CR4","unstructured":"Chen Z, Badrinarayanan V, Lee C-Y, Rabinovich A (2017) Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. arXiv preprint arXiv:1711.02257"},{"key":"3695_CR5","doi-asserted-by":"crossref","unstructured":"Ruder S, Bingel J, Augenstein I, S\u00f8gaard A (2019) Latent multi-task architecture learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 33, pp 4822\u20134829","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"3695_CR6","doi-asserted-by":"crossref","unstructured":"Liu S, Johns E, Davison A J (2019) End-to-end multi-task learning with attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1871\u20131880","DOI":"10.1109\/CVPR.2019.00197"},{"key":"3695_CR7","doi-asserted-by":"crossref","unstructured":"Guo M, Haque A, Huang D-A, Yeung S, Fei-Fei L (2018) Dynamic task prioritization for multitask learning. In: Proceedings of the European conference on computer vision (ECCV), pp 270\u2013287","DOI":"10.1007\/978-3-030-01270-0_17"},{"key":"3695_CR8","unstructured":"Lin X, Baweja H, Kantor G, Held D (2019) Adaptive auxiliary task weighting for reinforcement learning. In: Advances in Neural Information Processing Systems, pp 4773\u20134784"},{"issue":"1","key":"3695_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Flat minima. Neural Comput 9(1):1\u201342","journal-title":"Neural Comput"},{"issue":"4","key":"3695_CR10","doi-asserted-by":"publisher","first-page":"3939","DOI":"10.1007\/s10489-021-02224-6","volume":"52","author":"W Yuan","year":"2022","unstructured":"Yuan W, Hu F, Lu L (2022) A new non-adaptive optimization method: Stochastic gradient descent with momentum and difference. Appl Intell 52(4):3939\u20133953","journal-title":"Appl Intell"},{"key":"3695_CR11","unstructured":"Vandenhende S, Georgoulis S, De Brabandere B, Van Gool L (2020) Branched multi-task networks: deciding what layers to share. BMVC"},{"key":"3695_CR12","unstructured":"Bruggemann D, Kanakis M, Georgoulis S, Van Gool L (2020) Automated search for resource-efficient branched multi-task networks. arXiv:2008.10292"},{"key":"3695_CR13","doi-asserted-by":"publisher","first-page":"160035","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AlistairEW Johnson","year":"2016","unstructured":"Johnson Alistair EW, Pollard T J, Shen L, Li-wei H L, Feng M, Ghassemi M, Moody B, Szolovits P, Celi L A, Mark R G (2016) Mimic-iii, a freely accessible critical care database. Scientific data 3:160035","journal-title":"Scientific data"},{"key":"3695_CR14","doi-asserted-by":"crossref","unstructured":"Wei T, Wang S, Zhong J, Liu D, Zhang J (2021) A review on evolutionary multi-task optimization: Trends and challenges. IEEE Trans Evol Comput","DOI":"10.1109\/TEVC.2021.3139437"},{"issue":"1","key":"3695_CR15","first-page":"2853","volume":"17","author":"A Maurer","year":"2016","unstructured":"Maurer A, Pontil M, Romera-Paredes B (2016) The benefit of multitask representation learning. J Mach Learn Res 17(1):2853\u20132884","journal-title":"J Mach Learn Res"},{"key":"3695_CR16","doi-asserted-by":"crossref","unstructured":"Caruana R (1993) Multitask learning: A knowledge-based source of inductive bias. In: ICML","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"3695_CR17","doi-asserted-by":"crossref","unstructured":"Vandenhende S, Georgoulis S, Van Gansbeke W, Proesmans M, Dai D, Van Gool L (2021) Multi-task learning for dense prediction tasks: A survey. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2021.3054719"},{"issue":"1","key":"3695_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-019-0103-9","volume":"6","author":"H Harutyunyan","year":"2019","unstructured":"Harutyunyan H, Khachatrian H, Kale D C, Ver Steeg G, Galstyan A (2019) Multitask learning and benchmarking with clinical time series data. Scientific Data 6(1):1\u201318","journal-title":"Scientific Data"},{"key":"3695_CR19","unstructured":"Guo H, Pasunuru R, Bansal M (2019) Autosem: Automatic task selection and mixing in multi-task learning. arXiv preprint arXiv:1904.04153"},{"key":"3695_CR20","doi-asserted-by":"crossref","unstructured":"Zhang Z, Luo P, Loy C C, Tang X (2014) Facial landmark detection by deep multi-task learning. In: European conference on computer vision. Springer, pp 94\u2013108","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"3695_CR21","doi-asserted-by":"crossref","unstructured":"Bingel J, S\u00f8gaard A (2017) Identifying beneficial task relations for multi-task learning in deep neural networks. arXiv preprint arXiv:1702.0830","DOI":"10.18653\/v1\/E17-2026"},{"key":"3695_CR22","unstructured":"Rai P, Daum\u00e9 III H (2010) Infinite predictor subspace models for multitask learning. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp 613\u2013620"},{"key":"3695_CR23","doi-asserted-by":"crossref","unstructured":"Sun G, Probst T, Paudel D P, Popovi\u0107 N, Kanakis M, Patel J, Dai D, Van Gool L (2021) Task switching network for multi-task learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 8291\u20138300","DOI":"10.1109\/ICCV48922.2021.00818"},{"key":"3695_CR24","unstructured":"Romera-Paredes B, Argyriou A, Berthouze N, Pontil M (2012) Exploiting unrelated tasks in multi-task learning. In: International conference on artificial intelligence and statistics, pp 951\u2013959"},{"key":"3695_CR25","unstructured":"Fifty C, Amid E, Zhao Z, Yu T, Anil R, Finn C (2021) Efficiently identifying task groupings for multi-task learning. In: Ranzato M, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J (eds) Advances in Neural Information Processing Systems. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/e77910ebb93b511588557806310f78f1-Paper.pdf, vol 34. Curran Associates, Inc., pp 27503\u201327516"},{"key":"3695_CR26","doi-asserted-by":"publisher","first-page":"106884","DOI":"10.1016\/j.knosys.2021.106884","volume":"220","author":"Y Wu","year":"2021","unstructured":"Wu Y, Song Y, Huang H, Ye F, Xie X, Jin H (2021) Enhancing graph neural networks via auxiliary training for semi-supervised node classification. Knowl-Based Syst 220:106884","journal-title":"Knowl-Based Syst"},{"key":"3695_CR27","doi-asserted-by":"crossref","unstructured":"Yang Z, Zhang Y, Yu J, Cai J, Luo J (2018) End-to-end multi-modal multi-task vehicle control for self-driving cars with visual perceptions. In: 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, pp 2289\u20132294","DOI":"10.1109\/ICPR.2018.8546189"},{"key":"3695_CR28","doi-asserted-by":"publisher","first-page":"101918","DOI":"10.1016\/j.media.2020.101918","volume":"70","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Chen H, Li Y, Liu Q, Xu X, Wang S, Yap P-T, Shen D (2021) Multi-task learning for segmentation and classification of tumors in 3d automated breast ultrasound images. Med Image Anal 70:101918","journal-title":"Med Image Anal"},{"key":"3695_CR29","doi-asserted-by":"crossref","unstructured":"Verboven S, Martin N (2022) Combining the clinical and operational perspectives in heterogeneous treatment effect inference in healthcare processes. In: International Conference on Process Mining. Springer, pp 327\u2013339","DOI":"10.1007\/978-3-030-98581-3_24"},{"issue":"5","key":"3695_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3406095","volume":"53","author":"R Dabre","year":"2020","unstructured":"Dabre R, Chu C, Kunchukuttan A (2020) A survey of multilingual neural machine translation. ACM Computing Surveys (CSUR) 53(5):1\u201338","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"3695_CR31","unstructured":"Caruana R, Baluja S, Mitchell T (1996) Using the future to\u201d sort out\u201d the present: Rankprop and multitask learning for medical risk evaluation. In: Advances in neural information processing systems, pp 959\u2013965"},{"key":"3695_CR32","doi-asserted-by":"publisher","DOI":"10.1002\/9781119146841","volume-title":"Fraud analytics using descriptive, predictive, and social network techniques: a guide to data science for fraud detection","author":"B Baesens","year":"2015","unstructured":"Baesens B, Van Vlasselaer V, Verbeke W (2015) Fraud analytics using descriptive, predictive, and social network techniques: a guide to data science for fraud detection. Wiley, New York"},{"issue":"9","key":"3695_CR33","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1057\/palgrave.jors.2601990","volume":"56","author":"B Baesens","year":"2005","unstructured":"Baesens B, Van Gestel T, Stepanova M, Van den Poel D, Vanthienen J (2005) Neural network survival analysis for personal loan data. J Oper Res Soc 56(9):1089\u20131098","journal-title":"J Oper Res Soc"},{"key":"3695_CR34","unstructured":"Yu T, Kumar S, Gupta A, Levine S, Hausman K, Finn C (2020) Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782"},{"key":"3695_CR35","unstructured":"Kendall A, Gal Y, Cipolla R (2018) Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7482\u20137491"},{"key":"3695_CR36","unstructured":"Jean S, Firat O, Johnson M (2019) Adaptive scheduling for multi-task learning. arXiv preprint arXiv:1909.06434"},{"key":"3695_CR37","unstructured":"Sutton R S (1992) Adapting bias by gradient descent: An incremental version of delta-bar-delta. In: AAAI, pp 171\u2013176"},{"key":"3695_CR38","doi-asserted-by":"crossref","unstructured":"Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT\u20192010. Springer, pp 177\u2013186","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"3695_CR39","unstructured":"Kingma D P, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"3695_CR40","unstructured":"Smith S L, Le Q V (2017) A bayesian perspective on generalization and stochastic gradient descent. arXiv preprint arXiv:1710.06451"},{"key":"3695_CR41","unstructured":"McCandlish S, Kaplan J, Amodei D, Team OpenAI Dota (2018) An empirical model of large-batch training. arXiv preprint arXiv:1812.06162"},{"key":"3695_CR42","unstructured":"Keskar N S, Mudigere D, Nocedal J, Smelyanskiy M, Tang P T P (2016) On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836"},{"key":"3695_CR43","unstructured":"Zhang C, Liao Q, Rakhlin A, Miranda B, Golowich N, Poggio T (2018) Theory of deep learning iib: Optimization properties of sgd. arXiv preprint arXiv:1801.02254"},{"key":"3695_CR44","unstructured":"Golmant N, Vemuri N, Yao Z, Feinberg V, Gholami A, Rothauge K, Mahoney M W, Gonzalez J (2018) On the computational inefficiency of large batch sizes for stochastic gradient descent. arXiv preprint arXiv:1811.12941"},{"key":"3695_CR45","unstructured":"Goyal P, Doll\u00e1r P, Girshick R, Noordhuis P, Wesolowski L, Kyrola A, Tulloch A, Jia Y, He K (2017) Accurate, large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677"},{"key":"3695_CR46","unstructured":"Hoffer E, Hubara I, Soudry D (2017) Train longer, generalize better: closing the generalization gap in large batch training of neural networks. In: Advances in Neural Information Processing Systems, pp 1731\u20131741"},{"key":"3695_CR47","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: Towards balanced learning for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"3695_CR48","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, vol 33, pp 8577\u20138584","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"3695_CR49","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":"3695_CR50","doi-asserted-by":"crossref","unstructured":"Oksuz K, Cam B C, Kalkan S, Akbas E (2020) Imbalance problems in object detection: A review. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2020.2981890"},{"key":"3695_CR51","unstructured":"Ren M, Zeng W, Yang B, Urtasun R (2018) Learning to reweight examples for robust deep learning. In: International conference on machine learning. PMLR, pp 4334\u20134343"},{"issue":"1","key":"3695_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-021-04484-y","volume":"22","author":"TN Dong","year":"2021","unstructured":"Dong T N, Brogden G, Gerold G, Khosla M (2021) A multitask transfer learning framework for the prediction of virus-human protein\u2013protein interactions. BMC bioinformatics 22(1):1\u201324","journal-title":"BMC bioinformatics"},{"key":"3695_CR53","unstructured":"Caruana R (2000) Learning from imbalanced data: Rank metrics and extra tasks. In: Proc. Am. Assoc. for Artificial Intelligence (AAAI) Conf, pp 51\u201357"},{"issue":"5","key":"3695_CR54","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1097\/CCM.0b013e31820a92c6","volume":"39","author":"M Saeed","year":"2011","unstructured":"Saeed M, Villarroel M, Reisner A T, Clifford G, Lehman L-W, Moody G, Heldt T, Kyaw T H, Moody B, Mark R G (2011) Multiparameter intelligent monitoring in intensive care ii (mimic-ii): a public-access intensive care unit database. Critical Care Med 39(5):952","journal-title":"Critical Care Med"},{"key":"3695_CR55","doi-asserted-by":"crossref","unstructured":"Purushotham S, Meng C, Che Z, Liu Y (2017) Benchmark of deep learning models on large healthcare mimic datasets. arXiv preprint arXiv:1710.08531","DOI":"10.1016\/j.jbi.2018.04.007"},{"key":"3695_CR56","unstructured":"Johnson Alistair EW, Pollard T J, Mark R G (2017) Reproducibility in critical care: a mortality prediction case study. In: Machine Learning for Healthcare Conference, pp 361\u2013376"},{"key":"3695_CR57","doi-asserted-by":"crossref","unstructured":"Gentimis T, Ala\u2019J A, Durante A, Cook K, Steele R (2017) Predicting hospital length of stay using neural networks on mimic iii data. In: 2017 IEEE 15th Intl Conf on Dependable, Autonomic and Secure Computing, 15th Intl Conf on Pervasive Intelligence and Computing, 3rd Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC\/PiCom\/DataCom\/CyberSciTech). IEEE, pp 1194\u20131201","DOI":"10.1109\/DASC-PICom-DataCom-CyberSciTec.2017.191"},{"issue":"4","key":"3695_CR58","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1097\/CCM.0000000000002936","volume":"46","author":"S Nemati","year":"2018","unstructured":"Nemati S, Holder A, Razmi F, Stanley M D, Clifford G D, Buchman T G (2018) An interpretable machine learning model for accurate prediction of sepsis in the icu. Critical care medicine 46(4):547","journal-title":"Critical care medicine"},{"key":"3695_CR59","doi-asserted-by":"crossref","unstructured":"Suresh H, Gong J J, Guttag J V (2018) Learning tasks for multitask learning: Heterogenous patient populations in the icu. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp 802\u2013810","DOI":"10.1145\/3219819.3219930"},{"key":"3695_CR60","unstructured":"Harutyunyan H, Khachatrian H, Kale D C, Steeg G V, Galstyan A (2017) Multitask learning and benchmarking with clinical time series data. arXiv:1703.07771"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03695-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03695-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03695-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T11:27:30Z","timestamp":1656934050000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03695-x"}},"subtitle":["Highly Dynamic Task Weighting for Multitask Learning with Auxiliary Tasks"],"short-title":[],"issued":{"date-parts":[[2022,7,4]]},"references-count":60,"alternative-id":["3695"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03695-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2022,7,4]]},"assertion":[{"value":"29 April 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2022","order":2,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interest"}}]}}