{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T11:01:30Z","timestamp":1780743690220,"version":"3.54.1"},"reference-count":153,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Fraunhofer Research Center for Machine Learning"},{"name":"Competence Center for Machine Learning Rhine Ruhr ML2R","award":["01"],"award-info":[{"award-number":["01"]}]},{"name":"Competence Center for Machine Learning Rhine Ruhr ML2R","award":["S18038B"],"award-info":[{"award-number":["S18038B"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tkde.2021.3079836","type":"journal-article","created":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T19:52:41Z","timestamp":1620849161000},"page":"1-1","source":"Crossref","is-referenced-by-count":459,"title":["Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems"],"prefix":"10.1109","author":[{"given":"Laura","family":"von Rueden","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Mayer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Beckh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Georgiev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Giesselbach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raoul","family":"Heese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Birgit","family":"Kirsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michal","family":"Walczak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julius","family":"Pfrommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annika","family":"Pick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajkumar","family":"Ramamurthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jochen","family":"Garcke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Bauckhage","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jannis","family":"Schuecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Compensating data shortages in manufacturing with monotonicity knowledge","author":"schmid","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30484-3_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8621955"},{"key":"ref32","author":"abu-mostafa","year":"2012","journal-title":"Learning From Data"},{"key":"ref31","author":"gauch","year":"2003","journal-title":"Scientific Method in Practice"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005188"},{"key":"ref36","first-page":"537","article-title":"Knowledge-based support vector machine classifiers","author":"fung","year":"2003","journal-title":"Proc 15th Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30493-5_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/machines5010004"},{"key":"ref28","article-title":"From data mining to knowledge discovery in databases","volume":"17","author":"fayyad","year":"1996","journal-title":"AI Mag"},{"key":"ref27","volume":"19","author":"machamer","year":"2008","journal-title":"The Blackwell Guide to the Philosophy of Science"},{"key":"ref29","author":"kahneman","year":"2011","journal-title":"Thinking Fast and Slow"},{"key":"ref20","article-title":"Physics informed deep learning (part i): Data-driven solutions of nonlinear partial differential equations","author":"raissi","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2720168"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.08.011"},{"key":"ref24","article-title":"Relational inductive biases, deep learning, and graph networks","author":"battaglia","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.04.010"},{"key":"ref101","first-page":"624","article-title":"Learning with knowledge from multiple experts","author":"richardson","year":"2003","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/9781405164863.ch3"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994016"},{"key":"ref25","article-title":"Epistemiology","author":"steup","year":"2018","journal-title":"The Stanford Encyclopedia of Philosophy (Winter 2012 Edition)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2016.615"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21468\/SciPostPhys.5.3.028"},{"key":"ref153","article-title":"Towards a rigorous science of interpretable machine learning","author":"doshi-velez","year":"2017"},{"key":"ref150","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1445"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1165"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836233"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161"},{"key":"ref149","article-title":"Learning from human feedback: Challenges for real-world reinforcement learning in NLP","author":"kreutzer","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz199"},{"key":"ref58","article-title":"Incorporating causal prior knowledge as path-constraints in Bayesian networks and maximal ancestral graphs","author":"borboudakis","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02906-6_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783365"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2018.8621379"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008328630915"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)90105-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevFluids.3.074602"},{"key":"ref40","first-page":"33","article-title":"Informed machine learning through functional composition.","author":"bauckhage","year":"2018","journal-title":"LWDA"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","article-title":"Very deep convolutional networks for text classification","author":"conneau","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0337-2"},{"key":"ref8","article-title":"Toward trustworthy AI development: Mechanisms for supporting verifiable claims","author":"brundage","year":"2020"},{"key":"ref49","first-page":"7178","article-title":"End-to-end differentiable physics for learning and control","author":"belbute-peres","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2016.803"},{"key":"ref9","article-title":"Explainable machine learning for scientific insights and discoveries","author":"roscher","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.05.024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/72.712178"},{"key":"ref48","article-title":"Deep lagrangian networks: Using physics as model prior for deep learning","author":"lutter","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690381003"},{"key":"ref42","article-title":"Data-driven fluid simulations using regression forests","volume":"34","author":"jeong","year":"2015","journal-title":"ACM Trans Graph"},{"key":"ref41","article-title":"From deep to physics-informed learning of turbulence: Diagnostics","author":"king","year":"2018"},{"key":"ref44","article-title":"Deep learning for physical processes: Incorporating prior scientific knowledge","author":"pajot","year":"2017"},{"key":"ref43","article-title":"Physics-informed deep generative models","author":"yang","year":"2018"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70956-5_7"},{"key":"ref126","article-title":"Active learning literature survey","author":"settles","year":"2009"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA49011.2020.00069"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5399-7"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2014.07.018"},{"key":"ref72","first-page":"640","article-title":"Prior knowledge in support vector kernels","author":"sch\u00f6lkopf","year":"1998","journal-title":"Proc Conf Adv Neural Inf Process Syst"},{"key":"ref129","author":"kalnay","year":"2003","journal-title":"Atmospheric Modeling Data Assimilation and Predictability"},{"key":"ref71","article-title":"Exploiting cyclic symmetry in convolutional neural networks","author":"dieleman","year":"2016"},{"key":"ref128","first-page":"34","article-title":"Logical versus analogical or symbolic versus connectionist or neat versus scruffy","volume":"12","author":"minsky","year":"1991","journal-title":"AI Mag"},{"key":"ref70","first-page":"2990","article-title":"Group equivariant convolutional networks","author":"cohen","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/5.726787"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107706804"},{"key":"ref77","first-page":"1002","article-title":"Markov logic mixtures of gaussian processes: Towards machines reading regression data","author":"schiegg","year":"2012","journal-title":"Proc Artif Intell Statist"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.02.029"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.758"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618796"},{"key":"ref134","author":"steinwart","year":"2008","journal-title":"Support Vector Machines"},{"key":"ref131","first-page":"5938","article-title":"Self-supervised intrinsic image decomposition","author":"janner","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref78","first-page":"140","article-title":"Learning pipelines with limited data and domain knowledge: A study in parsing physics problems","author":"sachan","year":"2018","journal-title":"Neural Inf Process Syst"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/643"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref136","author":"lapidus","year":"2011","journal-title":"Numerical Solution Of Partial Differential Equations in Science and Engineering"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/s102080010030"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8205961"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmachtools.2006.04.007"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44584-3_43"},{"key":"ref62","article-title":"A compositional object-based approach to learning physical dynamics","author":"chang","year":"2016"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1021\/cm100795d"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098126"},{"key":"ref64","article-title":"Learning physical intuition of block towers by example","author":"lerer","year":"2016"},{"key":"ref65","first-page":"1","article-title":"Using simulation to improve sample-efficiency of Bayesian optimization for bipedal robots.","volume":"20","author":"rai","year":"2019","journal-title":"J Machine Learn Res"},{"key":"ref140","first-page":"62","article-title":"Hybrid neural systems: From simple coupling to fully integrated neural networks","volume":"2","author":"mcgarry","year":"1999","journal-title":"Neural Comput Surv"},{"key":"ref66","first-page":"1733","article-title":"Learning to exploit stability for 3D scene parsing","author":"du","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1002\/0470018860.s00035"},{"key":"ref142","article-title":"Neurosymbolic AI: The 3rd wave","author":"garcez","year":"2020"},{"key":"ref67","first-page":"2242","article-title":"Learning from simulated and unsupervised images through adversarial training","author":"shrivastava","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref143","article-title":"Imposing category trees onto word-embeddings using a geometric construction","author":"dong","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/22.643839"},{"key":"ref144","article-title":"Hinge-loss Markov random fields and probabilistic soft logic","author":"bach","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023283917997"},{"key":"ref145","article-title":"Scalable structure learning for probabilistic soft logic","author":"embar","year":"2018"},{"key":"ref1","first-page":"84","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.ijar.2006.06.009","article-title":"Bayesian network learning algorithms using structural restrictions","volume":"45","author":"castellano","year":"2007","journal-title":"Int J Approx Reasoning"},{"key":"ref109","article-title":"Right for the wrong scientific reasons: Revising deep networks by interacting with their explanations","author":"schramowski","year":"2020"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref108","article-title":"Interpretations are useful: Penalizing explanations to align neural networks with prior knowledge","author":"rieger","year":"2019"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/230"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/604045.604056"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1004"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2013.10.012"},{"key":"ref91","first-page":"1","article-title":"A short introduction to probabilistic soft logic","author":"kimmig","year":"2012","journal-title":"Proc NIPS Workshop Probabilistic Program Found Appl"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2012.6400486"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-5833-1"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref103","first-page":"4302","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2005.10.003"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5296-5"},{"key":"ref110","first-page":"10203","article-title":"Street-map based validation of semantic segmentation in autonomous driving","author":"wirtz","year":"2021","journal-title":"Proc Int Conf Pattern Recognit"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref99","article-title":"Beating atari with natural language guided reinforcement learning","author":"kaplan","year":"2017"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.02.050"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.212"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.00-37"},{"key":"ref11","article-title":"A semantic loss function for deep learning with symbolic knowledge","author":"xu","year":"0"},{"key":"ref12","article-title":"Physics-guided neural networks (PGNN): An application in lake temperature modeling","author":"karpatne","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10934"},{"key":"ref14","first-page":"4509","article-title":"Interaction networks for learning about objects, relations and physics","author":"battaglia","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.10"},{"key":"ref82","first-page":"501","article-title":"Symmetry constrained machine learning","author":"bergman","year":"2019","journal-title":"Proc SAI Intelligent Systems Conf"},{"key":"ref16","first-page":"1559","article-title":"Hybrid knowledge routed modules for large-scale object detection","author":"jiang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3191513"},{"key":"ref81","first-page":"1858","article-title":"Symbolic graph reasoning meets convolutions","author":"liang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1173"},{"key":"ref18","article-title":"Spigan: Privileged adversarial learning from simulation","author":"lee","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref83","first-page":"280","article-title":"Guiding semi-supervision with constraint-driven learning","author":"chang","year":"2007","journal-title":"Assoc Comput Linguist"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.046"},{"key":"ref119","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref114","article-title":"Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning","author":"garcez","year":"2019"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1012"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35085-6_6"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01574-8"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5392-1"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1288"},{"key":"ref121","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1186\/1752-0509-4-121"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-009-9133-x"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1228"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref87","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N16-1018","article-title":"Counter-fitting word vectors to linguistic constraints","author":"mrk\u0161i","year":"2016"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44848-9_9"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/4358933\/09429985.pdf?arnumber=9429985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T15:26:04Z","timestamp":1670513164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9429985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":153,"URL":"https:\/\/doi.org\/10.1109\/tkde.2021.3079836","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}