AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

Takeru Miyato, Shin‐ichi Maeda, Masanori Koyama, Shin Ishii

TPAMI 2018 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 2,967 citations (OpenAlex)

This paper tried a common change: Add data augmentation

add data augmentation to VAT+EntMin · CIFAR-10 semi-supervised · test error rate: 13.15 -> 10.55 Improved

What 689 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use virtual adversarial perturbation instead of random perturbation (RPT) (ablation)VAT · MNIST supervisedtest error rate: 0.84 -> 0.64Improved
use virtual adversarial perturbation instead of random perturbation (RPT) (ablation)VAT · CIFAR-10 supervisedtest error rate: 6.30 -> 5.81Improved
use virtual adversarial perturbation instead of random perturbation (RPT) (ablation)VAT · MNIST semi-supervised N_l=100test error rate: 6.81 -> 1.36Improved
use virtual adversarial perturbation instead of random perturbation (RPT) (ablation)VAT · CIFAR-10 semi-supervised Conv-Smalltest error rate: 18.56 -> 14.87Improved
use VAT instead of L2-constrained adversarial training (ablation)supervised MLP · MNIST supervisedtest error rate: 0.71 -> 0.64Improved
add VAT regularization to baseline (ablation)supervised MLP · MNIST supervisedtest error rate: 1.11 -> 0.64Improved
add conditional entropy minimization to VAT (ablation)Conv-Large · SVHN semi-supervisedtest error rate: 5.77 -> 4.28Improved
add conditional entropy minimization to VAT (ablation)Conv-Large · CIFAR-10 semi-supervisedtest error rate: 14.18 -> 13.15Improved
add data augmentation to VAT+EntMin (ablation)Conv-Large · CIFAR-10 semi-supervisedtest error rate: 13.15 -> 10.55Improved
increase power iterations K from 1 to 4 (ablation)VAT · CIFAR-10 semi-supervisedtest error rate: 14.18 -> 14.25No clear effect
average 9 random perturbation gradients in RPT to match VAT gradient variance (ablation)RPT · MNIST supervisedtest error rateNo clear effect
use larger epsilon beyond optimum (ablation)VAT · SVHN/CIFAR-10 semi-supervisedtest error rateHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy