Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

PrefGAN-BERT: integrating direct preference optimization into semi-supervised GAN-BERT for robust text

Dangguo Shao¹, Tianzheng Lai¹, Lei Ma²

¹Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650500, Yunnan, China.

Scientific Reports

|April 17, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

iDeep-Cancer: Predicting Cancer-Related circRNA-RBP Binding Sites Using a Hybrid Network Framework.

IEEE transactions on computational biology and bioinformatics·2025

Same author

MED-PPIS: Multi-order Moments External Graph Attention Network with Dual-Axis Attention for Protein-Protein Interaction Site Prediction.

Interdisciplinary sciences, computational life sciences·2025

Same author

Mol-SGGI: an attention-guided comprehensive molecular multi-representation learning and adaptive fusion framework for molecular property prediction.

Molecular diversity·2025

Same author

Multiscale and global-local U-Net for protein-protein interaction site prediction.

Computational biology and chemistry·2025

Same author

Research on prediction of human oral bioavailability of drugs based on improved deep forest.

Journal of molecular graphics & modelling·2024

Same author

AFANet: Adaptive feature aggregation for polyp segmentation.

Medical engineering & physics·2024

Same journal

Turbulent flow in a vortex separator with a directed pipe inlet.

Scientific reports·2026

Same journal

Systematic characteristic evaluation of clay-based cementitious material derived from calcium carbide residue and waste tile powder.

Scientific reports·2026

Same journal

Retraction Note: Improvement of a rapid diagnostic application of monoclonal antibodies against avian influenza H7 subtype virus using Europium nanoparticles.

Scientific reports·2026

Same journal

Applying large language models to spam detection in the Kazakh low-resource language setting.

Scientific reports·2026

Same journal

An open-source 3D printing system enabling in-situ freeze-thaw processing of hydrogels.

Scientific reports·2026

Same journal

An enhanced EfficientNet framework for automated waste classification using cosine annealing and label smoothing.

Scientific reports·2026

See all related articles

PrefGAN-BERT improves semi-supervised learning for text classification using preference optimization and an LSTM generator. This novel approach enhances accuracy and stability, outperforming existing methods, especially with limited labeled data.

Area of Science:

Artificial Intelligence
Natural Language Processing
Machine Learning

Background:

Semi-supervised learning (SSL) shows potential for text classification with scarce labeled data.
Existing methods face challenges with unstable adversarial training and poor utilization of unlabeled data.

Purpose of the Study:

To introduce PrefGAN-BERT, a novel framework integrating Direct Preference Optimization (DPO) into GAN-BERT for robust semi-supervised text classification.
To enhance adversarial training stability and unlabeled data utilization in text classification.

Main Methods:

Integrated Direct Preference Optimization (DPO) into GAN-BERT, reformulating adversarial training as a preference-ranking process.
Employed an LSTM-based generator to improve sequential modeling, feature diversity, and mitigate mode collapse.

Keywords:

BERT DPO LSTM generator Semi-supervised generative adversarial learning

Related Experiment Videos

Utilized the Bradley-Terry model for smoother gradients and stable discriminator convergence.

Main Results:

PrefGAN-BERT achieved superior performance compared to state-of-the-art semi-supervised and adversarial baselines across five benchmark datasets.
Demonstrated an average improvement of 6.1 percentage points over GAN-BERT, particularly under extremely low-label conditions.
Ablation studies confirmed DPO's effectiveness in enhancing feature separability and model interpretability.

Conclusions:

PrefGAN-BERT offers a scalable, theoretically interpretable, and robust framework for preference-guided semi-supervised text classification.
The proposed method effectively addresses limitations of existing GAN-based SSL models, improving accuracy and training stability.