{"id":26591757,"url":"https://github.com/arminarj/deepgcca-pytorch","last_synced_at":"2025-10-08T02:08:30.183Z","repository":{"id":201735624,"uuid":"266419609","full_name":"arminarj/DeepGCCA-pytorch","owner":"arminarj","description":"An implementation of Deep Generalized Canonical Correlation Analysis (DGCCA or Deep GCCA) with pytorch.","archived":false,"fork":false,"pushed_at":"2020-06-11T11:09:32.000Z","size":2743,"stargazers_count":48,"open_issues_count":2,"forks_count":13,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-09T11:52:48.972Z","etag":null,"topics":["cca","correlation","deepgcca","dgcca","multimodal","multiview","multiview-learning","statistics"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/arminarj.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-05-23T21:07:03.000Z","updated_at":"2024-10-27T03:42:59.000Z","dependencies_parsed_at":null,"dependency_job_id":"bd895f27-8b7e-48ed-bda9-b4b8afb4d1d9","html_url":"https://github.com/arminarj/DeepGCCA-pytorch","commit_stats":null,"previous_names":["arminarj/deepgcca-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/arminarj/DeepGCCA-pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arminarj%2FDeepGCCA-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arminarj%2FDeepGCCA-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arminarj%2FDeepGCCA-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arminarj%2FDeepGCCA-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arminarj","download_url":"https://codeload.github.com/arminarj/DeepGCCA-pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arminarj%2FDeepGCCA-pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278877092,"owners_count":26061381,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cca","correlation","deepgcca","dgcca","multimodal","multiview","multiview-learning","statistics"],"created_at":"2025-03-23T14:19:49.055Z","updated_at":"2025-10-08T02:08:30.157Z","avatar_url":"https://github.com/arminarj.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DGCCA-pytorch:\n\nA Pytorch Implementation of Deep Generalized Canonical Correlation Analysis as described in:\n\nAdrian Benton, Huda Khayrallah, Biman Gujral, Dee Ann Reisinger, Sheng Zhang, and Raman Arora. Deep Generalized Canonical Correlation Analysis. The 4th Workshop on Representation Learning for NLP. 2019\n[(Paper-link)](https://www.aclweb.org/anthology/W19-4301/)\n\n\n\n# Deep Generalized Canonical Correlation Analysis:\n\n\n*Generalized Canonical Correlation Analysis (GCCA)* is a method which corresponds to solving an optimization problom objective to find the best linear shared space called ***G*** for the *J* view of a data\n\n**DeepGCCA** is a non-linear version of GCCA which uses neural networks as the feature extractor functions instead of linear transformers. ***DGCCA*** is some how exention of ***DeepCCA*** for more than two views though it has a different objective function.\n\n![](./img/DGCCA.jpg)\n![](./img/GCCA-DGCCA-Benton.jpg)\n - figures source [Deep Generalized Canonical Correlation Analysis - Arxiv 1702.02519](https://arxiv.org/abs/1702.02519)\n\n## Pseudocode algorithm:\n\nPseudocode algorithm based on the paper,\n![](./img/psuedocode.jpg)\n\n# Example:\n\nSynthatic Data: [(synth data generator)](/synth_data.py)\n![](./img/Synth-data.jpg)\n\nDGCCA Latent space for views:\n![](./img/Lantent-space-views.jpg)\n\n - figures source [Deep Generalized Canonical Correlation Analysis - Arxiv 1702.02519](https://arxiv.org/abs/1702.02519)\n\n# Prerequest:\n\n- Python 3.6\u003e=\n- Pytorch 1.4 \u003e= (should also work with \u003e=1.0)\n- Numpy\n- Scipy\n- Seanborn\n\n# Other Implementations:\n\n - [Theano Implementation](https://bitbucket.org/adrianbenton/dgcca-py3/src/master/) By Adiran Benton.\n \n \n ## Notes:\n \n ### check list:\n \n - cuda test\n - Varient Batch sizes test\n \n ### to do: \n \n - Nan gradient/update rules (Famous issue of Deep CCA - based models, like [DeepCCA Nan outputs](https://github.com/Michaelvll/DeepCCA))\n - More numerical stabilization for varient Architectures\n \n Warmest thanks to Mr. Adrian Benton for his kind helps.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farminarj%2Fdeepgcca-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farminarj%2Fdeepgcca-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farminarj%2Fdeepgcca-pytorch/lists"}