Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:45854594, 2019.
Abstract
Generative models often use latent variables to represent structured variation in highdimensional data, such as images and medical waveforms. However, these latent variables may ignore subtle, yet meaningful features in the data. Some features may predict an outcome of interest (e.g. heart attack) but account for only a small fraction of variation in the data. We propose a generative model training objective that uses a blackbox discriminative model as a regularizer to learn representations that preserve this predictive variation. With these discriminatively regularized latent variable models, we visualize and measure variation in the data that influence a blackbox predictive model, enabling an expert to better understand each prediction. With this technique, we study models that use electrocardiograms to predict outcomes of clinical interest. We measure our approach on synthetic and real data with statistical summaries and an experiment carried out by a physician.
Related Material


