{"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/deep-generalized-canonical-correlation","title":"Deep Generalized Canonical Correlation Analysis","arxiv_id":"1702.02519","date":"2017-02-08","proceeding":"WS 2019 8","authors":["Adrian Benton","Huda Khayrallah","Biman Gujral","Dee Ann Reisinger","Sheng Zhang","Raman Arora"],"abstract":"We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a\nmethod for learning nonlinear transformations of arbitrarily many views of\ndata, such that the resulting transformations are maximally informative of each\nother. While methods for nonlinear two-view representation learning (Deep CCA,\n(Andrew et al., 2013)) and linear many-view representation learning\n(Generalized CCA (Horst, 1961)) exist, DGCCA is the first CCA-style multiview\nrepresentation learning technique that combines the flexibility of nonlinear\n(deep) representation learning with the statistical power of incorporating\ninformation from many independent sources, or views. We present the DGCCA\nformulation as well as an efficient stochastic optimization algorithm for\nsolving it. We learn DGCCA representations on two distinct datasets for three\ndownstream tasks: phonetic transcription from acoustic and articulatory\nmeasurements, and recommending hashtags and friends on a dataset of Twitter\nusers. We find that DGCCA representations soundly beat existing methods at\nphonetic transcription and hashtag recommendation, and in general perform no\nworse than standard linear many-view techniques.","url_abs":"http://arxiv.org/abs/1702.02519v2","url_pdf":"http://arxiv.org/pdf/1702.02519v2.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":"deep-generalized-canonical-correlation","repo_url":"https://bitbucket.org/adrianbenton/dgcca-py3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"deep-generalized-canonical-correlation","repo_url":"https://github.com/arminarj/deepgcca-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-generalized-canonical-correlation","repo_url":"https://github.com/jameschapman19/cca_zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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=1702.02519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02519"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jameschapman19/cca_zoo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arminarj/deepgcca-pytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://bitbucket.org/adrianbenton/dgcca-py3","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fd418704db68e2ea","entry":"GCCA_loss","repo":"arminarj/deepgcca-pytorch","repo_kind":"listed","path":"loss_objectives.py","file_url":"https://github.com/arminarj/deepgcca-pytorch/blob/HEAD/loss_objectives.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd418704db68e2ea"}},{"code_sha256_prefix":"b0f619d86cf9a839","entry":"create_synthData","repo":"arminarj/deepgcca-pytorch","repo_kind":"listed","path":"synth_data.py","file_url":"https://github.com/arminarj/deepgcca-pytorch/blob/HEAD/synth_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0f619d86cf9a839"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}