{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-deep-multi-view-representation-learning","title":"On Deep Multi-View Representation Learning: Objectives and Optimization","arxiv_id":"1602.01024","date":"2016-02-02","proceeding":null,"authors":["Weiran Wang","Raman Arora","Karen Livescu","Jeff Bilmes"],"abstract":"We consider learning representations (features) in the setting in which we\nhave access to multiple unlabeled views of the data for learning while only one\nview is available for downstream tasks. Previous work on this problem has\nproposed several techniques based on deep neural networks, typically involving\neither autoencoder-like networks with a reconstruction objective or paired\nfeedforward networks with a batch-style correlation-based objective. We analyze\nseveral techniques based on prior work, as well as new variants, and compare\nthem empirically on image, speech, and text tasks. We find an advantage for\ncorrelation-based representation learning, while the best results on most tasks\nare obtained with our new variant, deep canonically correlated autoencoders\n(DCCAE). We also explore a stochastic optimization procedure for minibatch\ncorrelation-based objectives and discuss the time/performance trade-offs for\nkernel-based and neural network-based implementations.","url_abs":"http://arxiv.org/abs/1602.01024v1","url_pdf":"http://arxiv.org/pdf/1602.01024v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-deep-multi-view-representation-learning","repo_url":"https://github.com/jiayueg/multimodal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.01024","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}