EXoN: EXplainable encoder Network
This work addresses the need for interpretable latent representations in machine learning, though it appears incremental as it builds on existing VAE and semi-supervised methods.
The paper tackles the problem of creating a customized and explainable latent space in Variational AutoEncoders for semi-supervised learning, resulting in reduced investigation costs for representation patterns on datasets like MNIST and CIFAR-10.
We propose a new semi-supervised learning method of Variational AutoEncoder (VAE) which yields a customized and explainable latent space by EXplainable encoder Network (EXoN). Customization means a manual design of latent space layout for specific labeled data. To improve the performance of our VAE in a classification task without the loss of performance as a generative model, we employ a new semi-supervised classification method called SCI (Soft-label Consistency Interpolation). The classification loss and the Kullback-Leibler divergence play a crucial role in constructing explainable latent space. The variability of generated samples from our proposed model depends on a specific subspace, called activated latent subspace. Our numerical results with MNIST and CIFAR-10 datasets show that EXoN produces an explainable latent space and reduces the cost of investigating representation patterns on the latent space.