Learning Interpretable Disentangled Representations using Adversarial VAEs
This work addresses the need for explainable AI in clinical practice by improving interpretability and performance in medical data analysis, though it is incremental as it builds on existing disentanglement methods.
The paper tackled the problem of learning interpretable disentangled representations for medical applications by introducing an adversarial variational autoencoder with a total correlation constraint, achieving a relative improvement of 81.50% in disentanglement, 11.60% in clustering, and 2% in supervised classification with limited labeled data.
Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact and explainable representation of the data. In this paper, we introduce a novel adversarial variational autoencoder with a total correlation constraint to enforce independence on the latent representation while preserving the reconstruction fidelity. Our proposed method is validated on a publicly available dataset showing that the learned disentangled representation is not only interpretable, but also superior to the state-of-the-art methods. We report a relative improvement of 81.50% in terms of disentanglement, 11.60% in clustering, and 2% in supervised classification with a few amounts of labeled data.