{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:33:33Z","timestamp":1774539213504,"version":"3.50.1"},"reference-count":24,"publisher":"MIT Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2016,2]]},"abstract":"<jats:p> Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)\u2013based approaches and autoencoder (AE)\u2013based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. <\/jats:p>","DOI":"10.1162\/neco_a_00801","type":"journal-article","created":{"date-parts":[[2015,12,14]],"date-time":"2015-12-14T20:53:04Z","timestamp":1450126384000},"page":"257-285","source":"Crossref","is-referenced-by-count":84,"title":["Correlational Neural Networks"],"prefix":"10.1162","volume":"28","author":[{"given":"Sarath","family":"Chandar","sequence":"first","affiliation":[{"name":"University of Montreal, Montreal QC H3T 1J4, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mitesh M.","family":"Khapra","sequence":"additional","affiliation":[{"name":"IBM Research India, Bangalore 560077, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugo","family":"Larochelle","sequence":"additional","affiliation":[{"name":"University of Sherbrooke, Sherbrooke QC J1K 2R1, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Balaraman","family":"Ravindran","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Madras, Chennai, India, 600036"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B5","volume-title":"Natural language processing with Python","author":"Bird Steven E. L.","year":"2009"},{"key":"B7","first-page":"1853","volume-title":"Advances in neural information proceesing systems","volume":"27","author":"Chandar S.","year":"2014"},{"key":"B8","first-page":"2493","volume":"12","author":"Collobert R.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2013.09.020"},{"key":"B10","first-page":"945","volume-title":"Proceedings of the 28th International Conference on Machine Learning","author":"Dauphin Y.","year":"2011"},{"key":"B11","first-page":"199","volume-title":"Advances in neural information processing systems","volume":"24","author":"Dhillon P.","year":"2011"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1066"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1006"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00067-8"},{"key":"B19","first-page":"1755","volume":"10","author":"King D. E.","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"B22","first-page":"21","volume-title":"Proceedings of the 2010 Named Entities Workshop","author":"Kumaran A.","year":"2010"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3115\/1699705.1699708"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1028"},{"key":"B25","first-page":"91","volume-title":"Advances in neural information processing systems","volume":"27","author":"Lu Y.","year":"2014"},{"key":"B28","first-page":"115","volume":"4","author":"Mishra S.","year":"2009","journal-title":"Journal of Applied Economic Sciences"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1111\/j.1551-6709.2010.01106.x"},{"key":"B32","first-page":"2825","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"B33","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Soyer H.","year":"2015"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s11336-011-9206-8"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-12275-0_10"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(76)90010-5"},{"key":"B38","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Zou W. Y.","year":"2013"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:41:08Z","timestamp":1615585268000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/28\/2\/257-285\/8141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2]]},"references-count":24,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["10.1162\/NECO_a_00801"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00801","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,2]]}}}