https://arxiv.org/abs/1511.05644
The adversarial autoencoder matches the aggregated posterior distribution of the latent representation of the autoencoder to an arbitrary prior distribution.
The result of the training is that the encoder learns to convert the data distribution to the prior distribution, while the decoder learns a deep generative model that maps the imposed prior to the data distribution.
To speak differently, the encoder maps the data distribution into a prior distritbution in a latent space, and then the decoder returns to the original distribution again. The rationale behind is that any sample generated from the latent space subjected to the prior could be meaningful.
The Adversarial training procedure is used to adjust the distritbution to certain prior, or limit the representation to certain form.
Here x is the data, and z is the code in the hidden space. The upper part is an autoencoder that build the one-to-one mapping between x and z. The lower part is the discriminator which force the distribution of z to match the prior p(z).
The discriminator guadually adjusts the distribution of generated samples to be indistinguishable from the real samples.
In AAE, the adversarial training procedure is to allow the codes generated by the encoder to match the prior distribution.