{"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/distributional-smoothing-with-virtual","title":"Distributional Smoothing with Virtual Adversarial Training","arxiv_id":"1507.00677","date":"2015-07-02","proceeding":null,"authors":["Takeru Miyato","Shin-ichi Maeda","Masanori Koyama","Ken Nakae","Shin Ishii"],"abstract":"We propose local distributional smoothness (LDS), a new notion of smoothness\nfor statistical model that can be used as a regularization term to promote the\nsmoothness of the model distribution. We named the LDS based regularization as\nvirtual adversarial training (VAT). The LDS of a model at an input datapoint is\ndefined as the KL-divergence based robustness of the model distribution against\nlocal perturbation around the datapoint. VAT resembles adversarial training,\nbut distinguishes itself in that it determines the adversarial direction from\nthe model distribution alone without using the label information, making it\napplicable to semi-supervised learning. The computational cost for VAT is\nrelatively low. For neural network, the approximated gradient of the LDS can be\ncomputed with no more than three pairs of forward and back propagations. When\nwe applied our technique to supervised and semi-supervised learning for the\nMNIST dataset, it outperformed all the training methods other than the current\nstate of the art method, which is based on a highly advanced generative model.\nWe also applied our method to SVHN and NORB, and confirmed our method's\nsuperior performance over the current state of the art semi-supervised method\napplied to these datasets.","url_abs":"http://arxiv.org/abs/1507.00677v9","url_pdf":"http://arxiv.org/pdf/1507.00677v9.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":"distributional-smoothing-with-virtual","repo_url":"https://github.com/takerum/vat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"distributional-smoothing-with-virtual","repo_url":"https://github.com/LYWH/oppo_face_vat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distributional-smoothing-with-virtual","repo_url":"https://github.com/ciolo/Sentiment-Analisys","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distributional-smoothing-with-virtual","repo_url":"https://github.com/likelion-hyeonjun/VAT_PYTORCH","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distributional-smoothing-with-virtual","repo_url":"https://github.com/lyakaap/VAT-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"distributional-smoothing-with-virtual","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/vat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.00677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.00677"}},"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/LYWH/oppo_face_vat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lyakaap/VAT-pytorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/takerum/vat","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ciolo/Sentiment-Analisys","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/4/vat","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/likelion-hyeonjun/VAT_PYTORCH","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"0332607c32976563","entry":"load_doc","repo":"ciolo/Sentiment-Analisys","repo_kind":"listed","path":"config.py","file_url":"https://github.com/ciolo/Sentiment-Analisys/blob/HEAD/config.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":"0332607c32976563"}},{"code_sha256_prefix":"991f57db31adb26a","entry":"load_embedding","repo":"ciolo/Sentiment-Analisys","repo_kind":"listed","path":"embedding.py","file_url":"https://github.com/ciolo/Sentiment-Analisys/blob/HEAD/embedding.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":"991f57db31adb26a"}},{"code_sha256_prefix":"37add9083e98f27a","entry":"validation","repo":"ciolo/Sentiment-Analisys","repo_kind":"listed","path":"train_and_evaluate.py","file_url":"https://github.com/ciolo/Sentiment-Analisys/blob/HEAD/train_and_evaluate.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":"37add9083e98f27a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}