Interpreting and generalizing deep learning in physics-based problems with functional linear models

TL;DR

This paper introduces generalized functional linear models as interpretable surrogates for deep learning in physics-based problems, improving out-of-distribution generalization and transparency while maintaining accuracy.

Contribution

It proposes a novel approach using functional linear models for interpreting and generalizing deep learning models in physics, with methods for training from neural networks or data.

Findings

Achieves comparable accuracy to deep learning models.

Improves out-of-distribution generalization.

Provides transparent, interpretable models.

Abstract

Although deep learning has achieved remarkable success in various scientific machine learning applications, its opaque nature poses concerns regarding interpretability and generalization capabilities beyond the training data. Interpretability is crucial and often desired in modeling physical systems. Moreover, acquiring extensive datasets that encompass the entire range of input features is challenging in many physics-based learning tasks, leading to increased errors when encountering out-of-distribution (OOD) data. In this work, motivated by the field of functional data analysis (FDA), we propose generalized functional linear models as an interpretable surrogate for a trained deep learning model. We demonstrate that our model could be trained either based on a trained neural network (post-hoc interpretation) or directly from training data (interpretable operator learning). A library of generalized functional linear models with different kernel functions is considered and sparse regression is used to discover an interpretable surrogate model that could be analytically presented. We present test cases in solid mechanics, fluid mechanics, and transport. Our results demonstrate that our model can achieve comparable accuracy to deep learning and can improve OOD generalization while providing more transparency and interpretability. Our study underscores the significance of interpretable representation in scientific machine learning and showcases the potential of functional linear models as a tool for interpreting and generalizing deep learning.