# Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder

Source: [Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder](<https://www.sota2.com/research/paper/68fa6d3c1e209131cea38a84>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:29:35.891Z

Authors: Zichuan Chen, Peng Liu

Published: 2021-09-30T01:40:39.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.14795>)

[PDF](<https://arxiv.org/pdf/2109.14795.pdf>)