Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation
This work addresses the challenge of robustness to environmental factors in machine learning for domains like physics or engineering, though it appears incremental as it builds on prior physics-informed methods.
The paper tackles the problem of learning robust data representations by integrating physical knowledge into variational autoencoders, resulting in improved extrapolation capabilities and interpretability compared to existing models.
The combination of machine learning models with physical models is a recent research path to learn robust data representations. In this paper, we introduce p$^3$VAE, a variational autoencoder that integrates prior physical knowledge about the latent factors of variation that are related to the data acquisition conditions. p$^3$VAE combines standard neural network layers with non-trainable physics layers in order to partially ground the latent space to physical variables. We introduce a semi-supervised learning algorithm that strikes a balance between the machine learning part and the physics part. Experiments on simulated and real data sets demonstrate the benefits of our framework against competing physics-informed and conventional machine learning models, in terms of extrapolation capabilities and interpretability. In particular, we show that p$^3$VAE naturally has interesting disentanglement capabilities. Our code and data have been made publicly available at https://github.com/Romain3Ch216/p3VAE.