Skip to main content

Learning autoencoders with relational regularization

Publication ,  Journal Article
Xu, H; Luo, D; Henao, R; Shah, S; Carin, L
Published in: 37th International Conference on Machine Learning, ICML 2020
January 1, 2020

A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a relational regularization on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the latent prior and its corresponding posterior, allowing one to flexibly learn a structured prior distribution associated with the generative model. Moreover, it helps co-training of multiple autoencoders even if they have heterogeneous architectures and incomparable latent spaces. We implement the framework with two scalable algorithms, making it applicable for both probabilistic and deterministic autoencoders. Our relational regularized autoencoder (RAE) outperforms existing methods, e.g., the variational autoencoder, Wasserstein autoencoder, and their variants, on generating images. Additionally, our relational co-training strategy for autoencoders achieves encouraging results in both synthesis and real-world multi-view learning tasks. The code is at https://github.com/HongtengXu/ Relational-AutoEncoders.

Duke Scholars

Published In

37th International Conference on Machine Learning, ICML 2020

Publication Date

January 1, 2020

Volume

PartF168147-14

Start / End Page

10507 / 10517
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Xu, H., Luo, D., Henao, R., Shah, S., & Carin, L. (2020). Learning autoencoders with relational regularization. 37th International Conference on Machine Learning, ICML 2020, PartF168147-14, 10507–10517.
Xu, H., D. Luo, R. Henao, S. Shah, and L. Carin. “Learning autoencoders with relational regularization.” 37th International Conference on Machine Learning, ICML 2020 PartF168147-14 (January 1, 2020): 10507–17.
Xu H, Luo D, Henao R, Shah S, Carin L. Learning autoencoders with relational regularization. 37th International Conference on Machine Learning, ICML 2020. 2020 Jan 1;PartF168147-14:10507–17.
Xu, H., et al. “Learning autoencoders with relational regularization.” 37th International Conference on Machine Learning, ICML 2020, vol. PartF168147-14, Jan. 2020, pp. 10507–17.
Xu H, Luo D, Henao R, Shah S, Carin L. Learning autoencoders with relational regularization. 37th International Conference on Machine Learning, ICML 2020. 2020 Jan 1;PartF168147-14:10507–10517.

Published In

37th International Conference on Machine Learning, ICML 2020

Publication Date

January 1, 2020

Volume

PartF168147-14

Start / End Page

10507 / 10517