Learning Sparse Latent Representations with the Deep Copula Information Bottleneck
This work addresses representation learning in deep latent variable models, offering an incremental improvement for tasks requiring sparse and disentangled features.
The paper tackled the shortcomings of the deep information bottleneck model by applying a copula transformation to restore invariance properties, leading to disentanglement and sparsity in the latent space, with evaluation on artificial and real data.
Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information bottleneck method, leads to disentanglement of the features in the latent space. Building on that, we show how this transformation translates to sparsity of the latent space in the new model. We evaluate our method on artificial and real data.