most citedImproving Variational Autoencoders with Density Gap-based Regularization

3 citations · 3 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2022★ 3 cited

Improving Variational Autoencoders with Density Gap-based Regularization

Jianfei Zhang, Jun Bai, Chenghua Lin +2

Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optim…