Pith. sign in

REVIEW 15 cited by

Adversarial Training Methods for Semi-Supervised Text Classification

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1605.07725 v4 pith:UAYK5VTL submitted 2016-05-25 stat.ML cs.LG

Takeru Miyato , Andrew M. Dai , Ian Goodfellow This is my paper · ORCID
classification stat.MLcs.LG
keywords adversarialtrainingsemi-supervisedsupervisedtextwordalgorithmsembeddings
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making small perturbations to numerous entries of the input vector, which is inappropriate for sparse high-dimensional inputs such as one-hot word representations. We extend adversarial and virtual 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. The proposed method achieves state of the art results on multiple benchmark semi-supervised and purely supervised tasks. We provide visualizations and analysis showing that the learned word embeddings have improved in quality and that while training, the model is less prone to overfitting. Code is available at https://github.com/tensorflow/models/tree/master/research/adversarial_text.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 15 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Dynamic Domain Information Modulation Algorithm for Multi-domain Sentiment Analysis

    cs.CL 2025-05 reject novelty 6.0 of 10

    A new algorithm (DAMA) learns a per-domain scalar step size that modulates the input's domain information via gradients, yielding a modest 0.3% average accuracy improvement over a multi-task baseline.

  2. Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning

    cs.CL 2024-12 conditional novelty 6.0 of 10

    SSU combines task-vector negation, random-label loss, and weight saliency to forget copyrighted books sequentially while retaining more general language ability than existing baselines.

  3. What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation

    cs.SE 2024-12 conditional novelty 6.0 of 10

    AUGER steers an LLM's attention toward predicted defective lines and thereby triggers 84 of 723 Defects4J bugs, outperforming five test-generation baselines.

  4. Improving Generalization in Coreference Resolution via Adversarial Training

    cs.CL 2019-08 conditional novelty 6.0 of 10

    Adversarial training on span representations slightly but generally improves coreference resolution accuracy, including on inputs whose named entities do not appear in training.

  5. Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning

    cs.CV 2019-08 conditional novelty 6.0 of 10

    Soft pseudo-labels combined with mixup and a guaranteed labeled-sample mini-batch count outperform consistency-regularization SSL methods on CIFAR-10/100, SVHN, and Mini-ImageNet.

  6. CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection

    cs.CR 2025-08 reject novelty 5.0 of 10

    A dual-track core-extraction defense reports near-zero jailbreak success on four attacks with preserved benign utility, but its safety-classifier component is undisclosed.

  7. ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model

    cs.LG 2025-07 conditional novelty 5.0 of 10

    ROBAD combines a transformer encoder-decoder with contrastive adversarial training to detect bad actors from user post sequences, achieving higher F1 and lower F1 drop under next-post attacks than baselines.

  8. Less is More: Adaptive Coverage for Synthetic Training Data

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A max-coverage graph algorithm with an adaptive similarity threshold selects 10-30% of synthetic data that trains classifiers as well as or better than the full dataset on sentiment, relation extraction, and NER tasks.

  9. RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition

    cs.CV 2025-02 conditional novelty 5.0 of 10

    RAMer achieves state-of-the-art multi-label emotion recognition on three benchmarks by combining reconstruction-based adversarial training, contrastive learning, a personality cue, and a stack shuffle augmentation to ...

  10. Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challenges

    cs.RO 2024-12 conditional novelty 5.0 of 10

    A survey of sonar-based deep learning that identifies robustness, dataset scarcity, and sim-to-real gaps as the main obstacles to safe underwater autonomy.

  11. Semi-supervised Thai Sentence Segmentation Using Local and Distant Word Representations

    cs.CL 2019-08 conditional novelty 5.0 of 10

    A Bi-LSTM-CRF with n-gram embeddings, self-attention, and modified Cross-View Training improves Thai sentence segmentation F1 to 92.5% on Orchid and 88.9% on UGWC, and punctuation restoration overall F1 to 65.2% on IWSLT.

  12. Robustness in AI-Generated Detection: Enhancing Resistance to Adversarial Attacks

    cs.CV 2025-05 conditional novelty 4.0 of 10

    Combining adversarial training with diffusion reconstruction error (DIRE) substantially improves face-generator detector accuracy under PGD attacks, but only the training attack is tested.

  13. Enhancing Generalization in Chain of Thought Reasoning for Smaller Models

    cs.LG 2025-01 reject novelty 4.0 of 10

    PRADA combines P-Tuning and domain-adversarial training with CoT distillation and claims improved cross-domain reasoning in small models, though the evaluation is confounded by target-data access.

  14. READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data

    cs.CL 2025-01 conditional novelty 4.0 of 10

    Combining an inverse-reinforcement-learning text generator with GAN-BERT-style adversarial training improves low-resource text classification on TREC and SST-5 benchmarks.

  15. Unifying Adversarial Perturbation for Graph Neural Networks

    cs.LG 2025-08 reject novelty 3.0 of 10

    Adding perturbations directly to every hidden embedding of a GNN is claimed to subsume existing feature-, edge-, and weight-perturbation defenses, but the claim rests on simplifications that the experiments do not act...

Pith tools