{"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/semi-supervised-deep-kernel-learning","title":"Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance","arxiv_id":"1805.10407","date":"2018-05-26","proceeding":"NeurIPS 2018 12","authors":["Neal Jean","Sang Michael Xie","Stefano Ermon"],"abstract":"Large amounts of labeled data are typically required to train deep learning\nmodels. For many real-world problems, however, acquiring additional data can be\nexpensive or even impossible. We present semi-supervised deep kernel learning\n(SSDKL), a semi-supervised regression model based on minimizing predictive\nvariance in the posterior regularization framework. SSDKL combines the\nhierarchical representation learning of neural networks with the probabilistic\nmodeling capabilities of Gaussian processes. By leveraging unlabeled data, we\nshow improvements on a diverse set of real-world regression tasks over\nsupervised deep kernel learning and semi-supervised methods such as VAT and\nmean teacher adapted for regression.","url_abs":"http://arxiv.org/abs/1805.10407v4","url_pdf":"http://arxiv.org/pdf/1805.10407v4.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":"semi-supervised-deep-kernel-learning","repo_url":"https://github.com/ermongroup/ssdkl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10407","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}