{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T19:04:02Z","timestamp":1774897442175,"version":"3.50.1"},"reference-count":91,"publisher":"Emerald","issue":"2-3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,6,12]]},"abstract":"<jats:p>Active learning is a protocol for supervised machine learning, in which a learning algorithm sequentially requests the labels of selected data points from a large pool of unlabeled data. This contrasts with passive learning, where the labeled data are taken at random. The objective in active learning is to produce a highly-accurate classifier, ideally using fewer labels than the number of random labeled data sufficient for passive learning to achieve the same. This article describes recent advances in our understanding of the theoretical benefits of active learning, and implications for the design of effective active learning algorithms. Much of the article focuses on a particular technique, namely disagreementbased active learning, which by now has amassed a mature and coherent literature. It also briefly surveys several alternative approaches from the literature. The emphasis is on theorems regarding the performance of a few general algorithms, including rigorous proofs where appropriate. However, the presentation is intended to be pedagogical, focusing on results that illustrate fundamental ideas, rather than obtaining the strongest or most general known theorems. The intended audience includes researchers and advanced graduate students in machine learning and statistics, interested in gaining a deeper understanding of the recent and ongoing developments in the theory of active learning.<\/jats:p>","DOI":"10.1561\/2200000037","type":"journal-article","created":{"date-parts":[[2014,6,12]],"date-time":"2014-06-12T09:16:30Z","timestamp":1402564590000},"page":"131-309","source":"Crossref","is-referenced-by-count":91,"title":["Theory of Disagreement-Based Active Learning"],"prefix":"10.1561","volume":"7","author":[{"given":"Steve","family":"Hanneke","sequence":"first","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2014,6,12]]},"reference":[{"key":"2026033014112122600_ref001","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/BF00318708","article-title":"Rates of growth and sample moduli for weighted empirical processes indexed by sets","volume":"75","author":"Alexander","year":"1987","journal-title":"Probability Theory and Related Fields"},{"key":"2026033014112122600_ref002","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511624216","volume-title":"Neural Network Learning: Theoretical Foundations","author":"Anthony","year":"1999"},{"key":"2026033014112122600_ref003","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1023\/A:1007454427662","article-title":"Strong minimax lower bounds for learning","volume":"30","author":"Antos","year":"1998","journal-title":"Machine Learning"},{"issue":"2","key":"2026033014112122600_ref004","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1214\/009053606000001217","article-title":"Fast learning rates for plug-in classifiers","volume":"35","author":"Audibert","year":"2007","journal-title":"The Annals of Statistics"},{"key":"2026033014112122600_ref005","article-title":"Robust interactive learning","volume-title":"Proceedings of the 25th Conference on Learning Theory","author":"Balcan","year":"2012"},{"key":"2026033014112122600_ref006","doi-asserted-by":"crossref","DOI":"10.1145\/1143844.1143853","article-title":"Agnostic active learning","volume-title":"Proceedings of the 23rd International Conference on Machine Learning","author":"Balcan","year":"2006"},{"key":"2026033014112122600_ref007","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-72927-3_5","article-title":"Margin based active learning","volume-title":"Proceedings of the 20th Conference on Learning Theory","author":"Balcan","year":"2007"},{"key":"2026033014112122600_ref008","article-title":"The true sample complexity of active learning","volume-title":"Proceedings of the 21st Conference on Learning Theory","author":"Balcan","year":"2008"},{"issue":"1","key":"2026033014112122600_ref009","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.jcss.2008.07.003","article-title":"Agnostic active learning","volume":"75","author":"Balcan","year":"2009","journal-title":"Journal of Computer and System Sciences"},{"issue":"2\u20133","key":"2026033014112122600_ref010","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s10994-010-5174-y","article-title":"The true sample complexity of active learning","volume":"80","author":"Balcan","year":"2010","journal-title":"Machine Learning"},{"issue":"1","key":"2026033014112122600_ref011","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1006\/jcss.2001.1794","article-title":"A new abstract combinatorial dimension for exact learning via queries","volume":"64","author":"Balc\u00e1zar","year":"2002","journal-title":"Journal of Computer and System Sciences"},{"key":"2026033014112122600_ref012","first-page":"138","article-title":"Convexity, classification, and risk bounds","volume-title":"Journal of the American Statistical Association","author":"Bartlett","year":"2006"},{"issue":"4","key":"2026033014112122600_ref013","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1214\/009053605000000282","article-title":"Local rademacher complexities","volume":"33","author":"Bartlett","year":"2005","journal-title":"The Annals of Statistics"},{"key":"2026033014112122600_ref014","doi-asserted-by":"crossref","DOI":"10.1145\/1553374.1553381","article-title":"Importance weighted active learning","volume-title":"Proceedings of the 26th International Conference on Machine Learning","author":"Beygelzimer","year":"2009"},{"key":"2026033014112122600_ref015","article-title":"Agnostic active learning without constraints","volume-title":"Advances in Neural Information Processing Systems 23","author":"Beygelzimer","year":"2010"},{"key":"2026033014112122600_ref016","article-title":"Efficient active learning","author":"Beygelzimer","year":"2011"},{"issue":"4","key":"2026033014112122600_ref017","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1145\/76359.76371","article-title":"Learnability and the Vapnik-Chervonenkis dimension","volume":"36","author":"Blumer","year":"1989","journal-title":"Journal of the Association for Computing Machinery"},{"key":"2026033014112122600_ref018","doi-asserted-by":"crossref","DOI":"10.1090\/surv\/062","volume-title":"Gaussian Measures","author":"Bogachev","year":"1998"},{"issue":"5","key":"2026033014112122600_ref019","doi-asserted-by":"crossref","first-page":"2339","DOI":"10.1109\/TIT.2008.920189","article-title":"Minimax bounds for active learning","volume":"54","author":"Castro","year":"2008","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026033014112122600_ref020","article-title":"Upper and lower error bounds for active learning","volume-title":"The 44th Annual Al lerton Conference on Communication, Control and Computing","author":"Castro","year":"2006"},{"key":"2026033014112122600_ref021","first-page":"71","article-title":"Learning noisy linear classifiers via adaptive and selective sampling","volume-title":"Machine Learning","author":"Cavallanti","year":"2011"},{"issue":"2","key":"2026033014112122600_ref022","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1023\/A:1022673506211","article-title":"Improving generalization with active learning","volume":"15","author":"Cohn","year":"1994","journal-title":"Machine Learning"},{"key":"2026033014112122600_ref023","first-page":"326","article-title":"Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition","volume-title":"IEEE Transactions on Electronic Computers","author":"Cover","year":"1965"},{"key":"2026033014112122600_ref024","article-title":"Coarse sample complexity bounds for active learning","volume-title":"Advances in Neural Information Processing Systems 18","author":"Dasgupta","year":"2005"},{"key":"2026033014112122600_ref025","first-page":"1767","article-title":"Two faces of active learning","volume-title":"Theoretical Computer Science","author":"Dasgupta","year":"2011"},{"key":"2026033014112122600_ref026","doi-asserted-by":"crossref","DOI":"10.1007\/11503415_17","article-title":"Analysis of perceptron-based active learning","volume-title":"Proceedings of the 18th Conference on Learning Theory","author":"Dasgupta","year":"2005"},{"key":"2026033014112122600_ref027","article-title":"A general agnostic active learning algorithm","volume-title":"Advances in Neural Information Processing Systems","author":"Dasgupta","year":"2007"},{"key":"2026033014112122600_ref028","first-page":"281","article-title":"Analysis of perceptron-based active learning","volume-title":"Journal of Machine Learning Research","author":"Dasgupta","year":"2009"},{"key":"2026033014112122600_ref029","article-title":"Robust selective sampling from single and multiple teachers","volume-title":"Proceedings of the 23rd Conference on Learning Theory","author":"Dekel","year":"2010"},{"key":"2026033014112122600_ref030","article-title":"Selective sampling and active learning from single and multiple teachers","volume-title":"Journal of Machine Learning Research, To Appear","author":"Dekel","year":"2012"},{"key":"2026033014112122600_ref031","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0711-5","volume-title":"A Probabilistic Theory of Pattern Recognition","author":"Devroye","year":"1996"},{"issue":"4","key":"2026033014112122600_ref032","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1214\/aop\/1176991978","article-title":"Universal Donsker classes and metric entropy","volume":"15","author":"Dudley","year":"1987","journal-title":"The Annals of Probability"},{"issue":"3","key":"2026033014112122600_ref033","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0890-5401(89)90002-3","article-title":"A general lower bound on the number of examples needed for learning","volume":"82","author":"Ehrenfeucht","year":"1989","journal-title":"Information and Computation"},{"key":"2026033014112122600_ref034","volume-title":"PhD thesis","author":"Eisenberg","year":"1992"},{"key":"2026033014112122600_ref035","first-page":"1605","article-title":"On the foundations of noise-free selective classification","volume-title":"Journal of Machine Learning Research","author":"El-Yaniv","year":"2010"},{"key":"2026033014112122600_ref036","first-page":"255","article-title":"Active learning via perfect selective classification","volume-title":"Journal of Machine Learning Research","author":"El-Yaniv","year":"2012"},{"issue":"2","key":"2026033014112122600_ref037","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1137\/070684914","article-title":"On agnostic learning of parities, monomials and halfspaces","volume":"39","author":"Feldman","year":"2009","journal-title":"SIAM Journal on Computing"},{"key":"2026033014112122600_ref038","first-page":"133","article-title":"Selective sampling using the query by committee algorithm","volume-title":"Machine Learning","author":"Freund","year":"1997"},{"key":"2026033014112122600_ref039","article-title":"Active learning for smooth problems","volume-title":"Proceedings of the 22nd Conference on Learning Theory","author":"Friedman","year":"2009"},{"issue":"3","key":"2026033014112122600_ref040","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1214\/009117906000000070","article-title":"Concentration inequalities and asymptotic results for ratio type empirical processes","volume":"34","author":"Gin\u00e9","year":"2006","journal-title":"The Annals of Probability"},{"key":"2026033014112122600_ref041","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1006\/jcss.1995.1003","article-title":"On the complexity of teaching","volume":"50","author":"Goldman","year":"1995","journal-title":"Journal of Computer and System Sciences"},{"issue":"2","key":"2026033014112122600_ref042","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1137\/070685798","article-title":"Hardness of learning halfspaces with noise","volume":"39","author":"Guruswami","year":"2009","journal-title":"SIAM Journal on Computing"},{"key":"2026033014112122600_ref043","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-72927-3_7","article-title":"Teaching dimension and the complexity of active learning","volume-title":"Proceedings of the 20th Conference on Learning Theory","author":"Hanneke","year":"2007"},{"key":"2026033014112122600_ref044","doi-asserted-by":"crossref","DOI":"10.1145\/1273496.1273541","article-title":"A bound on the label complexity of agnostic active learning","volume-title":"Proceedings of the 24th International Conference on Machine Learning","author":"Hanneke","year":"2007"},{"key":"2026033014112122600_ref045","article-title":"Adaptive rates of convergence in active learning","volume-title":"Proceedings of the 22nd Conference on Learning Theory","author":"Hanneke","year":"2009"},{"key":"2026033014112122600_ref046","volume-title":"PhD thesis","author":"Hanneke","year":"2009"},{"issue":"1","key":"2026033014112122600_ref047","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1214\/10-AOS843","article-title":"Rates of convergence in active learning","volume":"39","author":"Hanneke","year":"2011","journal-title":"The Annals of Statistics"},{"issue":"5","key":"2026033014112122600_ref048","first-page":"1469","article-title":"Activized learning: Transforming passive to active with improved label complexity","volume":"13","author":"Hanneke","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"2026033014112122600_ref049","unstructured":"S.\n              Hanneke\n            \n          . Theory of Active Learning, 2014. URL http:\/\/www.stat.cmu.edu\/~shanneke."},{"key":"2026033014112122600_ref050","article-title":"Negative results for active learning with convex losses","volume-title":"Proceedings of the 13th International Conference on Artificial Intel ligence and Statistics","author":"Hanneke","year":"2010"},{"key":"2026033014112122600_ref051","volume-title":"Surrogate losses in passive and active learning","author":"Hanneke","year":"2012"},{"key":"2026033014112122600_ref052","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/0890-5401(92)90010-D","article-title":"Decision theoretic generalizations of the PAC model for neural net and other learning applications","volume":"100","author":"Haussler","year":"1992","journal-title":"Information and Computation"},{"key":"2026033014112122600_ref053","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/0097-3165(95)90052-7","article-title":"Sphere packing numbers for subsets of the boolean n-cube with bounded Vapnik-Chervonenkis dimension","volume":"69","author":"Haussler","year":"1995","journal-title":"Journal of Combinatorial Theory A"},{"key":"2026033014112122600_ref054","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1006\/inco.1994.1097","article-title":"Predicting {0, 1}-functions on randomly drawn points","volume":"115","author":"Haussler","year":"1994","journal-title":"Information and Computation"},{"key":"2026033014112122600_ref055","doi-asserted-by":"crossref","DOI":"10.1145\/225298.225311","article-title":"Generalized teaching dimension and the query complexity of learning","volume-title":"Proceedings of the 8th Conference on Computational Learning Theory","author":"Heged\u00fcs","year":"1995"},{"key":"2026033014112122600_ref056","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1023\/A:1022696716689","article-title":"Learning nested differences of intersection-closed concept classes","volume":"5","author":"Helmbold","year":"1990","journal-title":"Machine Learning"},{"key":"2026033014112122600_ref057","volume-title":"PhD thesis","author":"Hsu","year":"2010"},{"key":"2026033014112122600_ref058","doi-asserted-by":"crossref","DOI":"10.1007\/11894841_9","article-title":"Active learning in the non-realizable case","volume-title":"Proceedings of the 17th International Conference on Algorithmic Learning Theory","author":"K\u00e4\u00e4ri\u00e4inen","year":"2006"},{"key":"2026033014112122600_ref059","doi-asserted-by":"crossref","DOI":"10.1109\/SFCS.2005.13","article-title":"Agnostically learning halfspaces","volume-title":"Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science","author":"Kalai","year":"2005"},{"key":"2026033014112122600_ref060","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1023\/A:1022615600103","article-title":"Toward efficient agnostic learning","volume":"17","author":"Kearns","year":"1994","journal-title":"Machine Learning"},{"issue":"6","key":"2026033014112122600_ref061","first-page":"2593","article-title":"Local rademacher complexities and oracle inequalities in risk minimization","volume":"34","author":"Koltchinskii","year":"2006","journal-title":"The Annals of Statistics"},{"key":"2026033014112122600_ref062","first-page":"2457","article-title":"Rademacher complexities and bounding the excess risk in active learning","volume":"11","author":"Koltchinskii","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"2026033014112122600_ref063","doi-asserted-by":"crossref","DOI":"10.21236\/ADA217331","article-title":"On metric entropy, Vapnik-Chervonenkis dimension, and learnability for a class of distributions","volume-title":"Technical Report CICS-P-160, Center for Intelligent Control Systems","author":"Kulkarni","year":"1989"},{"key":"2026033014112122600_ref064","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1023\/A:1022627018023","article-title":"Active learning using arbitrary binary valued queries","volume":"11","author":"Kulkarni","year":"1993","journal-title":"Machine Learning"},{"issue":"1","key":"2026033014112122600_ref065","doi-asserted-by":"crossref","first-page":"66","DOI":"10.3923\/ajms.2011.66.70","article-title":"Concise formulas for the area and volume of a hyperspherical cap","volume":"4","author":"Li","year":"2011","journal-title":"Asian Journal of Mathematics and Statistics"},{"key":"2026033014112122600_ref066","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1023\/A:1022869011914","article-title":"Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm","volume":"2","author":"Littlestone","year":"1988","journal-title":"Machine Learning"},{"issue":"6","key":"2026033014112122600_ref067","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1109\/72.471352","article-title":"On the sample complexity of PAC learning halfspaces against the uniform distribution","volume":"6","author":"Long","year":"1995","journal-title":"IEEE Transactions on Neural Networks"},{"key":"2026033014112122600_ref068","article-title":"A note on active learning for smooth problems","volume-title":"arXiv:1103.3095","author":"Mahalanabis","year":"2011"},{"key":"2026033014112122600_ref069","author":"Mahalanabis","year":"2012","journal-title":"PhD thesis"},{"key":"2026033014112122600_ref070","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1214\/aos\/1017939240","article-title":"Smooth discrimination analysis","volume":"27","author":"Mammen","year":"1999","journal-title":"The Annals of Statistics"},{"issue":"5","key":"2026033014112122600_ref071","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1214\/009053606000000786","article-title":"Risk bounds for statistical learning","volume":"34","author":"Massart","year":"2006","journal-title":"The Annals of Statistics"},{"key":"2026033014112122600_ref072","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1109\/TIT.2002.1013137","article-title":"Improving the sample complexity using global data","volume":"48","author":"Mendelson","year":"2002","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"2026033014112122600_ref073","first-page":"67","article-title":"Plug-in approach to active learning","volume":"13","author":"Minsker","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"2026033014112122600_ref074","volume-title":"Topology","author":"Munkres","year":"2000","edition":"2nd"},{"key":"2026033014112122600_ref075","doi-asserted-by":"crossref","DOI":"10.1109\/ALLERTON.2008.4797609","article-title":"Generalized binary search","volume-title":"Proceedings of the 46th Al lerton Conference on Communication, Control, and Computing","author":"Nowak","year":"2008"},{"issue":"12","key":"2026033014112122600_ref076","doi-asserted-by":"crossref","DOI":"10.1109\/TIT.2011.2169298","article-title":"The geometry of generalized binary search","volume":"57","author":"Nowak","year":"2011","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026033014112122600_ref077","volume-title":"NSF-CBMS Regional Conference Series in Probability and Statistics, Vol. 2","author":"Pollard","year":"1990"},{"key":"2026033014112122600_ref078","article-title":"Lower bounds for passive and active learning","volume-title":"Advances in Neural Information Processing Systems 24","author":"Raginsky","year":"2011"},{"key":"2026033014112122600_ref079","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"issue":"1","key":"2026033014112122600_ref080","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1214\/aos\/1079120131","article-title":"Optimal aggregation of classifiers in statistical learning","volume":"32","author":"Tsybakov","year":"2004","journal-title":"The Annals of Statistics"},{"issue":"11","key":"2026033014112122600_ref081","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1145\/1968.1972","article-title":"A theory of the learnable","volume":"27","author":"Valiant","year":"1984","journal-title":"Communications of the ACM"},{"key":"2026033014112122600_ref082","volume-title":"Empirical Processes in M-Estimation","author":"van de Geer","year":"2000"},{"key":"2026033014112122600_ref083","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1214\/11-EJS605","article-title":"A local maximal inequality under uniform entropy","volume":"5","author":"van der Vaart","year":"2011","journal-title":"Electronic Journal of Statistics"},{"key":"2026033014112122600_ref084","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2545-2","volume-title":"Weak Convergence and Empirical Processes","author":"van der Vaart","year":"1996"},{"key":"2026033014112122600_ref085","volume-title":"Estimation of Dependencies Based on Empirical Data","author":"Vapnik","year":"1982"},{"key":"2026033014112122600_ref086","volume-title":"Statistical Learning Theory","author":"Vapnik","year":"1998"},{"key":"2026033014112122600_ref087","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1137\/1116025","article-title":"On the uniform convergence of relative frequencies of events to their probabilities","volume":"16","author":"Vapnik","year":"1971","journal-title":"Theory of Probability and its Applications"},{"issue":"2","key":"2026033014112122600_ref088","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1214\/aoms\/1177731118","article-title":"Sequential tests of statistical hypotheses","volume":"16","author":"Wald","year":"1945","journal-title":"The Annals of Mathematical Statistics"},{"key":"2026033014112122600_ref089","first-page":"2269","article-title":"Smoothness, disagreement coefficient, and the label complexity of agnostic active learning","volume":"12","author":"Wang","year":"2011","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"2026033014112122600_ref090","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1137\/0306011","article-title":"A counterexample in stochastic optimum control","volume":"6","author":"Witsenhausen","year":"1968","journal-title":"SIAM Journal of Control"},{"issue":"1","key":"2026033014112122600_ref091","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1214\/aos\/1079120130","article-title":"Statistical behavior and consistency of classification methods based on convex risk minimization","volume":"32","author":"Zhang","year":"2004","journal-title":"The Annals of Statistics"}],"container-title":["Foundations and Trends\u00ae in Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftmal\/article-pdf\/7\/2-3\/131\/11154001\/2200000037en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftmal\/article-pdf\/7\/2-3\/131\/11154001\/2200000037en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:11:40Z","timestamp":1774894300000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftmal\/article\/7\/2-3\/131\/1332385\/Theory-of-Disagreement-Based-Active-Learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6,12]]},"references-count":91,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2014,6,12]]}},"URL":"https:\/\/doi.org\/10.1561\/2200000037","relation":{},"ISSN":["1935-8237","1935-8245"],"issn-type":[{"value":"1935-8237","type":"print"},{"value":"1935-8245","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,6,12]]}}}