Deep Diffusion Autoencoders

Extending work by Mishne et al., we propose Deep Diffusion Autoencoders (DDA) that learn an encoder-decoder map using a composite loss function that simultaneously minimizes the reconstruction error at the output layer and the distance to a Diffusion Map embedding in the bottleneck layer. These DDA are thus able to reconstruct new patterns from points in the embedding space in a way that preserves the geometry of the sample and, as a consequence, our experiments show that they may provide a powerful tool for data augmentation.