Publication Type
Working Paper
Version
publishedVersion
Publication Date
9-2021
Abstract
VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that could better aid the image classification tasks.
Discipline
Finance | Finance and Financial Management
Research Areas
Finance
First Page
1
Last Page
7
Citation
CHEN, Zichuan and LIU, Peng.
Towards better data augmentation using Wasserstein distance in variational auto-encoder. (2021). 1-7.
Available at: https://ink.library.smu.edu.sg/lkcsb_research/7046
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.