{"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/vigan-missing-view-imputation-with-generative","title":"VIGAN: Missing View Imputation with Generative Adversarial Networks","arxiv_id":"1708.06724","date":"2017-08-22","proceeding":null,"authors":["Chao Shang","Aaron Palmer","Jiangwen Sun","Ko-Shin Chen","Jin Lu","Jinbo Bi"],"abstract":"In an era when big data are becoming the norm, there is less concern with the\nquantity but more with the quality and completeness of the data. In many\ndisciplines, data are collected from heterogeneous sources, resulting in\nmulti-view or multi-modal datasets. The missing data problem has been\nchallenging to address in multi-view data analysis. Especially, when certain\nsamples miss an entire view of data, it creates the missing view problem.\nClassic multiple imputations or matrix completion methods are hardly effective\nhere when no information can be based on in the specific view to impute data\nfor such samples. The commonly-used simple method of removing samples with a\nmissing view can dramatically reduce sample size, thus diminishing the\nstatistical power of a subsequent analysis. In this paper, we propose a novel\napproach for view imputation via generative adversarial networks (GANs), which\nwe name by VIGAN. This approach first treats each view as a separate domain and\nidentifies domain-to-domain mappings via a GAN using randomly-sampled data from\neach view, and then employs a multi-modal denoising autoencoder (DAE) to\nreconstruct the missing view from the GAN outputs based on paired data across\nthe views. Then, by optimizing the GAN and DAE jointly, our model enables the\nknowledge integration for domain mappings and view correspondences to\neffectively recover the missing view. Empirical results on benchmark datasets\nvalidate the VIGAN approach by comparing against the state of the art. The\nevaluation of VIGAN in a genetic study of substance use disorders further\nproves the effectiveness and usability of this approach in life science.","url_abs":"http://arxiv.org/abs/1708.06724v5","url_pdf":"http://arxiv.org/pdf/1708.06724v5.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":"vigan-missing-view-imputation-with-generative","repo_url":"https://github.com/chaoshangcs/VIGAN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"matrix-completion","task_name":"Matrix Completion"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"denoising-autoencoder","method_name":"Denoising Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.06724","atlas_url":"https://app.syntology.ai/?focus=1708.06724","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}