Adversarially Regularized Autoencoders

Junbo (Jake) Zhao, Yoon Kim, Kelly Zhang, Alexander M. Rush, Yann LeCun

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: While autoencoders are a key technique in representation learning for continuous structures, such as images or wave forms, developing general-purpose autoencoders for discrete structures, such as text sequence or discretized images, has proven to be more challenging. In particular, discrete inputs make it more difficult to learn a smooth encoder that preserves the complex local relationships in the input space. In this work, we propose an adversarially regularized autoencoder (ARAE) with the goal of learning more robust discrete-space representations. ARAE jointly trains both a rich discrete-space encoder, such as an RNN, and a simpler continuous space generator function, while using generative adversarial network (GAN) training to constrain the distributions to be similar. This method yields a smoother contracted code space that maps similar inputs to nearby codes, and also an implicit latent variable GAN model for generation. Experiments on text and discretized images demonstrate that the GAN model produces clean interpolations and captures the multimodality of the original space, and that the autoencoder produces improvements in semi-supervised learning as well as state-of-the-art results in unaligned text style transfer task using only a shared continuous-space representation.
  • TL;DR: Adversarially Regularized Autoencoders learn smooth representations of discrete structures allowing for interesting results in text generation, such as unaligned style transfer, semi-supervised learning, and latent space interpolation and arithmetic.
  • Keywords: representation learning, natural language generation, discrete structure modeling, adversarial training, unaligned text style-transfer