{"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/smooth-neighbors-on-teacher-graphs-for-semi","title":"Smooth Neighbors on Teacher Graphs for Semi-supervised Learning","arxiv_id":"1711.00258","date":"2017-11-01","proceeding":"CVPR 2018 6","authors":["Yucen Luo","Jun Zhu","Mengxi Li","Yong Ren","Bo Zhang"],"abstract":"The recently proposed self-ensembling methods have achieved promising results\nin deep semi-supervised learning, which penalize inconsistent predictions of\nunlabeled data under different perturbations. However, they only consider\nadding perturbations to each single data point, while ignoring the connections\nbetween data samples. In this paper, we propose a novel method, called Smooth\nNeighbors on Teacher Graphs (SNTG). In SNTG, a graph is constructed based on\nthe predictions of the teacher model, i.e., the implicit self-ensemble of\nmodels. Then the graph serves as a similarity measure with respect to which the\nrepresentations of \"similar\" neighboring points are learned to be smooth on the\nlow-dimensional manifold. We achieve state-of-the-art results on\nsemi-supervised learning benchmarks. The error rates are 9.89%, 3.99% for\nCIFAR-10 with 4000 labels, SVHN with 500 labels, respectively. In particular,\nthe improvements are significant when the labels are fewer. For the\nnon-augmented MNIST with only 20 labels, the error rate is reduced from\nprevious 4.81% to 1.36%. Our method also shows robustness to noisy labels.","url_abs":"http://arxiv.org/abs/1711.00258v2","url_pdf":"http://arxiv.org/pdf/1711.00258v2.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":"smooth-neighbors-on-teacher-graphs-for-semi","repo_url":"https://github.com/xinmei9322/SNTG","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.00258","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}