Virtual Adversarial Training for Semi-Supervised Text Classification

By Takeru Miyato, Andrew M. Dai, Ian J. Goodfellow. 2016

96 citations recorded by the source corpus.

Subfields: Natural Language Processing, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Representation & Self-Supervised Learning

Citations in the corpus

MaskGAN: Better Text Generation via Filling in the ______ (2018, background): “They have shown impressive results in language modeling (Mikolov et al., 2010), machine translation (Wu et al., 2016) and text classiﬁcation (Miyato et al., 2017).”
Co-teaching: Robust training of deep neural networks with extremely noisy labels (2018, methodology): “Namely, the 9-layer CNN architecture in our paper follows “Temporal Ensembling” [21] and “Virtual Adversarial Training” [29], since the network structure we used here is standard test bed for weakly-supervised learning.”
Adversarial Dropout for Supervised and Semi-supervised Learning (2017, background): “…2014; Kurakin, Goodfellow, and Bengio 2016) defines g(x, y,θ) as g(y) ignoring x and θ, so g(y) is an one-hot encoding vector of y. • Virtual adversarial training (VAT) (Miyato et al. 2015; Miyato, Dai, and Goodfellow 2016) defines g(x, y,θ) as fθ̂(x) where θ̂ is the current estimated parameter.”
Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records (2017, methodology): “Generally speaking, existing methods include feature augmentation [33], virtual adversarial training [34], and joint training [35].”
How does Disagreement Help Generalization against Label Corruption? (2019, methodology): “Namely, the 9-layer CNN architecture in our paper follows “Temporal Ensembling” [13] and “Virtual Adversarial Training” [24].”
Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level (2016, background): “Long-Short Term Memory networks (LSTMs) [2] have also been shown to perform well on this task, rivaling or sometimes exceeding CNNs [5, 8].”
Adversarial Distillation for Efficient Recommendation with External Knowledge (2018, methodology): “[33] extend adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself.”
Adversarial Deep Structural Networks for Mammographic Mass Segmentation (2016, background): “The adversarial examples can be used to force the model to learn more robust features, which is a novel regularization technique for deep networks and can yield better performance than the base deep networks [11, 21, 20].”
A DIRT-T Approach to Unsupervised Domain Adaptation (2018, methodology): “In principle, our method can be applied to any domain adaptation tasks so long as one can define a reasonable notion of neighborhood for virtual adversarial training (Miyato et al., 2016).”
Adversarial Examples for Malware Detection (2017, background): “There are many more variants of adversarial training [15,11,23], all slightly differing in their objectives from the original version introduced by Goodfellow et al.”