{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:20Z","timestamp":1750220600052,"version":"3.41.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T00:00:00Z","timestamp":1614902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003086","name":"Basque Government","doi-asserted-by":"crossref","award":["IT-1244-19"],"award-info":[{"award-number":["IT-1244-19"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Elkartek","award":["KK-2020\/00049"],"award-info":[{"award-number":["KK-2020\/00049"]}]},{"name":"Spanish Ministry of Economy, Industry and Competitiveness","award":["TIN2016-78365-R"],"award-info":[{"award-number":["TIN2016-78365-R"]}]},{"DOI":"10.13039\/501100004837","name":"Spanish Ministry of Science and Innovation","doi-asserted-by":"crossref","award":["PID2019-104966GB-I00"],"award-info":[{"award-number":["PID2019-104966GB-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2021,4,30]]},"abstract":"<jats:p>Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks. From classifying hand-written characters of different alphabets to figuring out how to play several Atari games using reinforcement learning, multi-task models have been able to widen their performance range across different tasks, although these tasks are usually of a similar nature. In this work, we attempt to expand this range even further, by including heterogeneous tasks in a single learning procedure. To do so, we firstly formally define a multi-network model, identifying the necessary components and characteristics to allow different adaptations of said model depending on the tasks it is required to fulfill. Secondly, employing the formal definition as a starting point, we develop an illustrative model example consisting of three different tasks (classification, regression, and data sampling). The performance of this illustrative model is then analyzed, showing its capabilities. Motivated by the results of the analysis, we enumerate a set of open challenges and future research lines over which the full potential of the proposed model definition can be exploited.<\/jats:p>","DOI":"10.1145\/3434748","type":"journal-article","created":{"date-parts":[[2021,3,5]],"date-time":"2021-03-05T11:11:56Z","timestamp":1614942716000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Automatic Construction of Multi-Network Models for Heterogeneous Multi-Task Learning"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2425-8340","authenticated-orcid":false,"given":"Unai","family":"Garciarena","sequence":"first","affiliation":[{"name":"University of the Basque Country (UPV\/EHU), Gizpukoa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Mendiburu","sequence":"additional","affiliation":[{"name":"University of the Basque Country (UPV\/EHU), Gizpukoa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Santana","sequence":"additional","affiliation":[{"name":"University of the Basque Country (UPV\/EHU), Gizpukoa, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,3,5]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489387"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-018-9339-y"},{"key":"e_1_2_1_3_1","volume-title":"Understanding disentangling in -VAE. arXiv preprint arXiv:1804.03599","author":"Burgess Christopher P.","year":"2018","unstructured":"Christopher P. Burgess , Irina Higgins , Arka Pal , Loic Matthey , Nick Watters , Guillaume Desjardins , and Alexander Lerchner . 2018. Understanding disentangling in -VAE. arXiv preprint arXiv:1804.03599 ( 2018 ). Christopher P. Burgess, Irina Higgins, Arka Pal, Loic Matthey, Nick Watters, Guillaume Desjardins, and Alexander Lerchner. 2018. Understanding disentangling in -VAE. arXiv preprint arXiv:1804.03599 (2018)."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"e_1_2_1_7_1","volume-title":"Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734","author":"Fernando Chrisantha","year":"2017","unstructured":"Chrisantha Fernando , Dylan Banarse , Charles Blundell , Yori Zwols , David Ha , Andrei A. Rusu , Alexander Pritzel , and Daan Wierstra . 2017 . Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017). Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, and Daan Wierstra. 2017. Pathnet: Evolution channels gradient descent in super neural networks. arXiv preprint arXiv:1701.08734 (2017)."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2018.8477662"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.003"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205550"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205645"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015015"},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research). Yee Whye Teh and Mike Titterington (Eds.)","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio . 2010 . Understanding the difficulty of training deep feedforward neural networks . In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research). Yee Whye Teh and Mike Titterington (Eds.) , Vol. 9 . PMLR, Chia Laguna Resort, Sardinia, Italy, 249--256. Retrieved from http:\/\/proceedings.mlr.press\/v9\/glorot10a.html. Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research). Yee Whye Teh and Mike Titterington (Eds.), Vol. 9. PMLR, Chia Laguna Resort, Sardinia, Italy, 249--256. Retrieved from http:\/\/proceedings.mlr.press\/v9\/glorot10a.html."},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems. MIT Press","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron Courville , and Yoshua Bengio . 2014 . Generative adversarial nets . In Proceedings of the 27th International Conference on Neural Information Processing Systems. MIT Press , Cambridge, MA, 2672--2680. DOI:https:\/\/doi.org\/10.5555\/2969033.2969125 10.5555\/2969033.2969125 Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems. MIT Press, Cambridge, MA, 2672--2680. DOI:https:\/\/doi.org\/10.5555\/2969033.2969125"},{"key":"e_1_2_1_15_1","volume-title":"Salakhutdinov","author":"Hinton Geoffrey E.","year":"2006","unstructured":"Geoffrey E. Hinton and Ruslan R . Salakhutdinov . 2006 . Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504--507. Geoffrey E. Hinton and Ruslan R. Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504--507."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_17_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard , Menglong Zhu , Bo Chen , Dmitry Kalenichenko , Weijun Wang , Tobias Weyand , Marco Andreetto , and Hartwig Adam . 2017 . Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017). Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1125--1134","author":"Isola Phillip","key":"e_1_2_1_18_1","unstructured":"Phillip Isola , Jun-Yan Zhu , Tinghui Zhou , and Alexei A. Efros . 2017. Image-to-image translation with conditional adversarial networks . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1125--1134 . Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. 2017. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1125--1134."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"e_1_2_1_20_1","unstructured":"Su Jianlin. 2017. A Baseline of Fashion MNIST (MobileNet 95%). Retrieved from https:\/\/kexue.fm\/archives\/4556.  Su Jianlin. 2017. A Baseline of Fashion MNIST (MobileNet 95%). Retrieved from https:\/\/kexue.fm\/archives\/4556."},{"key":"e_1_2_1_21_1","volume-title":"Kingma and Max Welling","author":"Diederik","year":"2013","unstructured":"Diederik P. Kingma and Max Welling . 2013 . Auto-encoding variational Bayes . arXiv preprint arXiv:1312.6114 (2013). Diederik P. Kingma and Max Welling. 2013. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-14bd3278-006"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3122034"},{"key":"e_1_2_1_24_1","volume-title":"Learning Multiple Layers of Features from Tiny Images. Master\u2019s Thesis. Department of Computer Science","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky . 2009. Learning Multiple Layers of Features from Tiny Images. Master\u2019s Thesis. Department of Computer Science , University of Toronto . Retrieved from https:\/\/www.cs.toronto.edu\/ kriz\/learning-features- 2009 -TR.pdf. Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Master\u2019s Thesis. Department of Computer Science, University of Toronto. Retrieved from https:\/\/www.cs.toronto.edu\/ kriz\/learning-features-2009-TR.pdf."},{"key":"e_1_2_1_25_1","volume-title":"Hinton","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E . Hinton . 2012 . Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems . 1097--1105. DOI:https:\/\/doi.org\/10.5555\/2999134.2999257 10.5555\/2999134.2999257 Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems. 1097--1105. DOI:https:\/\/doi.org\/10.5555\/2999134.2999257"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172193"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205489"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2544314"},{"key":"e_1_2_1_31_1","volume-title":"Beyond shared hierarchies: Deep multitask learning through soft layer ordering. arXiv preprint arXiv:1711.00108","author":"Meyerson Elliot","year":"2017","unstructured":"Elliot Meyerson and Risto Miikkulainen . 2017. Beyond shared hierarchies: Deep multitask learning through soft layer ordering. arXiv preprint arXiv:1711.00108 ( 2017 ). Elliot Meyerson and Risto Miikkulainen. 2017. Beyond shared hierarchies: Deep multitask learning through soft layer ordering. arXiv preprint arXiv:1711.00108 (2017)."},{"volume-title":"Artificial Intelligence in the Age of Neural Networks and Brain Computing","author":"Miikkulainen Risto","key":"e_1_2_1_32_1","unstructured":"Risto Miikkulainen , Jason Liang , Elliot Meyerson , Aditya Rawal , Daniel Fink , Olivier Francon , Bala Raju , Hormoz Shahrzad , Arshak Navruzyan , Nigel Duffy , and Babak Hodjat . 2019. Evolving deep neural networks . In Artificial Intelligence in the Age of Neural Networks and Brain Computing , Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito (Eds.). Academic Press , 293--312. DOI:https:\/\/doi.org\/10.1016\/B978-0-12-815480-9.00015-3 10.1016\/B978-0-12-815480-9.00015-3 Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Daniel Fink, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, and Babak Hodjat. 2019. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing, Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito (Eds.). Academic Press, 293--312. DOI:https:\/\/doi.org\/10.1016\/B978-0-12-815480-9.00015-3"},{"key":"e_1_2_1_33_1","volume-title":"Miller and Peter Thomson","author":"Julian","year":"2000","unstructured":"Julian F. Miller and Peter Thomson . 2000 . Cartesian genetic programming. In Proceedings of the European Conference on Genetic Programming. Springer , 121--132. Julian F. Miller and Peter Thomson. 2000. Cartesian genetic programming. In Proceedings of the European Conference on Genetic Programming. Springer, 121--132."},{"volume-title":"Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning.","author":"Netzer Yuval","key":"e_1_2_1_34_1","unstructured":"Yuval Netzer , Tao Wang , Adam Coates , Alessandro Bissacco , Bo Wu , and Andrew Y. Ng . 2011. Reading digits in natural images with unsupervised feature learning . In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning. Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning."},{"volume-title":"Proceedings of the 2016 on Genetic and Evolutionary Computation Conference. ACM, 485--492","author":"Olson Randal S.","key":"e_1_2_1_35_1","unstructured":"Randal S. Olson , Nathan Bartley , Ryan J. Urbanowicz , and Jason H. Moore . 2016. Evaluation of a tree-based pipeline optimization tool for automating data science . In Proceedings of the 2016 on Genetic and Evolutionary Computation Conference. ACM, 485--492 . Randal S. Olson, Nathan Bartley, Ryan J. Urbanowicz, and Jason H. Moore. 2016. Evaluation of a tree-based pipeline optimization tool for automating data science. In Proceedings of the 2016 on Genetic and Evolutionary Computation Conference. ACM, 485--492."},{"volume-title":"Grammatical Evolution","author":"O\u2019Neil Michael","key":"e_1_2_1_36_1","unstructured":"Michael O\u2019Neil and Conor Ryan . 2003. Grammatical evolution . In Grammatical Evolution . Springer , 33--47. Michael O\u2019Neil and Conor Ryan. 2003. Grammatical evolution. In Grammatical Evolution. Springer, 33--47."},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems. 3308--3318","author":"Srivastava Akash","year":"2017","unstructured":"Akash Srivastava , Lazar Valkov , Chris Russell , Michael U. Gutmann , and Charles Sutton . 2017 . Veegan: Reducing mode collapse in GANs using implicit variational learning . In Proceedings of the Advances in Neural Information Processing Systems. 3308--3318 . Akash Srivastava, Lazar Valkov, Chris Russell, Michael U. Gutmann, and Charles Sutton. 2017. Veegan: Reducing mode collapse in GANs using implicit variational learning. In Proceedings of the Advances in Neural Information Processing Systems. 3308--3318."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071229"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2895748"},{"key":"e_1_2_1_42_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv: cs.LG\/1708.07747.  Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. arXiv: cs.LG\/1708.07747."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"e_1_2_1_44_1","volume-title":"Smart multitask Bregman clustering and multitask kernel clustering. ACM Transactions on Knowledge Discovery from Data 10, 1","author":"Zhang Xianchao","year":"2015","unstructured":"Xianchao Zhang , Xiaotong Zhang , and Han Liu . 2015. Smart multitask Bregman clustering and multitask kernel clustering. ACM Transactions on Knowledge Discovery from Data 10, 1 ( 2015 ), 8. Xianchao Zhang, Xiaotong Zhang, and Han Liu. 2015. Smart multitask Bregman clustering and multitask kernel clustering. ACM Transactions on Knowledge Discovery from Data 10, 1 (2015), 8."},{"key":"e_1_2_1_45_1","volume-title":"A survey on multi-task learning. arXiv preprint arXiv:1707.08114","author":"Zhang Yu","year":"2017","unstructured":"Yu Zhang and Qiang Yang . 2017. A survey on multi-task learning. arXiv preprint arXiv:1707.08114 ( 2017 ). Yu Zhang and Qiang Yang. 2017. A survey on multi-task learning. arXiv preprint arXiv:1707.08114 (2017)."},{"key":"e_1_2_1_46_1","volume-title":"A regularization approach to learning task relationships in multitask learning. ACM Transactions on Knowledge Discovery from Data 8, 3","author":"Zhang Yu","year":"2014","unstructured":"Yu Zhang and Dit-Yan Yeung . 2014. A regularization approach to learning task relationships in multitask learning. ACM Transactions on Knowledge Discovery from Data 8, 3 ( 2014 ), 12. Yu Zhang and Dit-Yan Yeung. 2014. A regularization approach to learning task relationships in multitask learning. ACM Transactions on Knowledge Discovery from Data 8, 3 (2014), 12."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00224"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3434748","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3434748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:31:58Z","timestamp":1750195918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3434748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,5]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,4,30]]}},"alternative-id":["10.1145\/3434748"],"URL":"https:\/\/doi.org\/10.1145\/3434748","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2021,3,5]]},"assertion":[{"value":"2019-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}