Variational autoencoder based synthetic data generation for imbalanced learning

Wan, Zhiqiang; Zhang, Yazhou; He, Haibo

doi:10.1109/ssci.2017.8285168

Cited by 99 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since VAEs learn variations in the data, they can be used for data augmentation to effectively improve performance of the downstream tasks [137] [138]. This is especially useful in imbalanced dataset problems and few-shot learning where a few classes may have low representation in the dataset [139].…”

Section: ) Medical Image Augmentation For Down-stream Tasksmentioning

confidence: 99%

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

Wei

Mahmood

2021

IEEE Access

View full text Add to dashboard Cite

Section: ) Medical Image Augmentation For Down-stream Tasksmentioning

confidence: 99%

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

Wei

Mahmood

2021

IEEE Access

View full text Add to dashboard Cite

“…For instance, a study by [ 29 ] explored the beneficial use of VAEs in the case of imbalanced datasets. To this end, they extracted an imbalanced subset of the popular MNIST dataset.…”

Section: Related Workmentioning

confidence: 99%

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data

et al. 2021

View full text Add to dashboard Cite

Over the past decade, deep learning has achieved unprecedented successes in a diversity of application domains, given large-scale datasets. However, particular domains, such as healthcare, inherently suffer from data paucity and imbalance. Moreover, datasets could be largely inaccessible due to privacy concerns, or lack of data-sharing incentives. Such challenges have attached significance to the application of generative modeling and data augmentation in that domain. In this context, this study explores a machine learning-based approach for generating synthetic eye-tracking data. We explore a novel application of variational autoencoders (VAEs) in this regard. More specifically, a VAE model is trained to generate an image-based representation of the eye-tracking output, so-called scanpaths. Overall, our results validate that the VAE model could generate a plausible output from a limited dataset. Finally, it is empirically demonstrated that such approach could be employed as a mechanism for data augmentation to improve the performance in classification tasks.

show abstract

“…Wan et al proposed a VAE-based synthetic data generation method for imbalanced learning. The VAE has better performance than the traditional synthetic sampling methods [28]. To extend reproduction of demonstration motion, the VAE is applied to generate time-series data in [29,30].…”

Section: Literature Reviewmentioning

confidence: 99%

Data-Driven EV Load Profiles Generation Using a Variational Auto-Encoder

et al. 2019

View full text Add to dashboard Cite

Although the penetration of electric vehicles (EVs) in distribution networks can improve the energy saving and emission reduction effects, its random and uncertain nature limits the ability of distribution networks to accept the load of EVs. To this end, establishing a load profile model of EV charging stations accurately and reasonably is of great significance to the planning, operation and scheduling of power system. Traditional generation methods for EV load profiles rely too much on experience, and need to set up a power load probability distribution in advance. In this paper, we propose a data-driven approach for load profiles of EV generation using a variational automatic encoder. Firstly, an encoder composed of deep convolution networks and a decoder composed of transposed convolution networks are trained using the original load profiles. Then, the new load profiles are obtained by decoding the random number which obeys a normal distribution. The simulation results show that EV load profiles generated by the deep convolution variational auto-encoder can not only retain the temporal correlation and probability distribution nature of the original load profiles, but also have a good restorative effect on the time distribution and fluctuation nature of the original power load.

show abstract

Variational autoencoder based synthetic data generation for imbalanced learning

Cited by 99 publications

References 17 publications

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

Recent Advances in Variational Autoencoders With Representation Learning for Biomedical Informatics: A Survey

Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data

Data-Driven EV Load Profiles Generation Using a Variational Auto-Encoder

Contact Info

Product

Resources

About