Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstruction

TL;DR

This paper investigates how latent representations in implicit neural networks affect the reconstruction of physical fields, using explainability methods to understand their impact and improve model performance.

Contribution

It introduces explainability techniques to analyze latent spaces in implicit neural networks for scientific field reconstruction, enhancing interpretability and understanding.

Findings

Latent representations contain contextual information affecting performance

Explainability methods reveal the influence of latent space on model outcomes

Preliminary results show improved understanding of model behavior

Abstract

Learning a continuous and reliable representation of physical fields from sparse sampling is challenging and it affects diverse scientific disciplines. In a recent work, we present a novel model called MMGN (Multiplicative and Modulated Gabor Network) with implicit neural networks. In this work, we design additional studies leveraging explainability methods to complement the previous experiments and further enhance the understanding of latent representations generated by the model. The adopted methods are general enough to be leveraged for any latent space inspection. Preliminary results demonstrate the contextual information incorporated in the latent representations and their impact on the model performance. As a work in progress, we will continue to verify our findings and develop novel explainability approaches.