Interpretable VAEs for nonlinear group factor analysis
This work addresses the need for interpretable generative models in scientific and financial applications where understanding interactions among grouped variables is crucial, representing an incremental advancement over traditional linear latent factor models.
The paper tackled the problem of making deep generative models interpretable for grouped data by introducing an output interpretable VAE (oi-VAE) that models nonlinear latent-to-observed relationships, demonstrating meaningful interpretability and improved generalization in motion capture and MEG data analyses.
Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data. Far less attention has been paid to making these generative models interpretable. In many scenarios, ranging from scientific applications to finance, the observed variables have a natural grouping. It is often of interest to understand systems of interaction amongst these groups, and latent factor models (LFMs) are an attractive approach. However, traditional LFMs are limited by assuming a linear correlation structure. We present an output interpretable VAE (oi-VAE) for grouped data that models complex, nonlinear latent-to-observed relationships. We combine a structured VAE comprised of group-specific generators with a sparsity-inducing prior. We demonstrate that oi-VAE yields meaningful notions of interpretability in the analysis of motion capture and MEG data. We further show that in these situations, the regularization inherent to oi-VAE can actually lead to improved generalization and learned generative processes.