InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood
This work addresses the challenge of creating comprehensive and interpretable data representations for machine learning applications, though it appears incremental as it builds on existing VAE and GAN methods.
The authors tackled the problem of learning joint interpretable representations by combining Variational Autoencoders and Generative Adversarial Networks, resulting in a model called InfoVAEGAN that learns discrete and continuous representations unsupervised using mutual information maximization and two-stage optimization.
Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold. In this paper, we propose a novel representation learning algorithm which combines the inference abilities of Variational Autoencoders (VAE) with the generalization capability of Generative Adversarial Networks (GAN). The proposed model, called InfoVAEGAN, consists of three networks~: Encoder, Generator and Discriminator. InfoVAEGAN aims to jointly learn discrete and continuous interpretable representations in an unsupervised manner by using two different data-free log-likelihood functions onto the variables sampled from the generator's distribution. We propose a two-stage algorithm for optimizing the inference network separately from the generator training. Moreover, we enforce the learning of interpretable representations through the maximization of the mutual information between the existing latent variables and those created through generative and inference processes.