Instability analysis for generative adversarial networks and its solving techniques

Tan, Hongwei; Zhou, Liwei; Wang, Guodong; Zhang, Zili

doi:10.1360/ssi-2019-0205

Cited by 3 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The generator and discriminator reached a balance after approximately 1500 steps, at which point the monitor stopped training. The stability of GAN training is closely related to the variations of D loss and G loss and their corresponding gradient changes [33]. Therefore, on the premise of performing STFT preprocessing on the EEG signals, the stability of network iteration training for DCGAN and WGAN-GP generators and discriminators is compared.…”

Section: Analysis and Experimental Results On Network Stabilitymentioning

confidence: 99%

“…Secondly, the WGAN-GP is used as an unsupervised feature learning model. This model uses Earth-Mover (EM) distance as a measure instead of Jensen-Shannon (JS) divergence to overcome training instability and model collapse issues, ensuring the richness of generated samples [32,33]. Lastly, a Bi-LSTM classification model is employed as the backend classifier, using a small amount of labeled STFT spectrograms to guide the prediction task.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-Supervised Seizure Prediction Model Combining Generative Adversarial Networks and Long Short-Term Memory Networks

Yang,

Liu,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

In recent years, significant progress has been made in seizure prediction using machine learning methods. However, fully supervised learning methods often rely on a large amount of labeled data, which can be costly and time-consuming. Unsupervised learning overcomes these drawbacks but can suffer from issues such as unstable training and reduced prediction accuracy. In this paper, we propose a semi-supervised seizure prediction model called WGAN-GP-Bi-LSTM. Specifically, we utilize the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) as the feature learning model, using the Earth Mover’s distance and gradient penalty to guide the unsupervised training process and train a high-order feature extractor. Meanwhile, we built a prediction model based on the Bidirectional Long Short-Term Memory Network (Bi-LSTM), which enhances seizure prediction performance by incorporating the high-order time-frequency features of the brain signals. An independent, publicly available dataset, CHB-MIT, was applied to train and validate the model’s performance. The results showed that the model achieved an average AUC of 90.08%, an average sensitivity of 82.84%, and an average specificity of 85.97%. A comparison with previous research demonstrates that our proposed method outperforms traditional adversarial network models and optimizes unsupervised feature extraction for seizure prediction.

show abstract

Section: Analysis and Experimental Results On Network Stabilitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Seizure Prediction Model Combining Generative Adversarial Networks and Long Short-Term Memory Networks

Yang,

Liu,

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In the generative adversarial networks, the number of parameters increases exponentially with the number of generating layers, which leads to an increase in the amplitude of parameter variation and increases the probability of gradient explosion. By adding spectral normalization to the generator and discriminator respectively [ 29 ], the gradient upper bound of the function is restricted to make the function smoother, improve the stability of parameter variation and reduce the probability of gradient explosion.…”

Section: C-dcgan For Bearing Fault Diagnosismentioning

confidence: 99%

A Rolling Bearing Fault Diagnosis Based on Conditional Depth Convolution Countermeasure Generation Networks under Small Samples

Cheng

Zhang

2022

Sensors

View full text Add to dashboard Cite

Aiming at the problems of low fault diagnosis accuracy caused by insufficient samples and unbalanced data sample distribution in bearing fault diagnosis, this paper proposes a fault diagnosis method for rolling bearings referencing conditional deep convolution adversarial generative networks (C−DCGAN) for efficient data augmentation. Firstly, the concept of conditional constraints is used to guide and improve the sample generation process of the original generative adversarial network, and specific constraints are added to the data generation model to perform a balanced expansion of muti-category fault data for small sample data sets. Secondly, aiming at the phenomena of training instability, gradient disappearance and gradient explosion in the imbalanced sample set, it is proposed to optimize the structure of the generative network by using the structure of self-defined skip connections and spectral normalization, while using the Wasserstein distance with penalty term instead of cross entropy. The function is used as the loss function of the generative adversarial network to improve the stable feature extraction ability of the generative network and the effect of the training process; in this way, simulation sample data with only a small variation from the real data distribution can be generated. Finally, the complete fault data set (after mixing the original data with sufficient fault category and sample number) and the generated data are input into the one-dimensional convolution neural network for fault diagnosis of rolling bearing. The experiment’s results show that the diagnosis method in this paper can improve the fault classification effect of rolling bearings by generating balanced and sufficient sample data.

show abstract

A WGAN-Based Method for Generating Malicious Domain Training Data

Zhang,

Huang,

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Instability analysis for generative adversarial networks and its solving techniques

Cited by 3 publications

References 6 publications

Semi-Supervised Seizure Prediction Model Combining Generative Adversarial Networks and Long Short-Term Memory Networks

Semi-Supervised Seizure Prediction Model Combining Generative Adversarial Networks and Long Short-Term Memory Networks

A Rolling Bearing Fault Diagnosis Based on Conditional Depth Convolution Countermeasure Generation Networks under Small Samples

A WGAN-Based Method for Generating Malicious Domain Training Data

Contact Info

Product

Resources

About