English

A robust estimator of mutual information for deep learning interpretability

Data Analysis, Statistics and Probability 2023-04-12 v2 Instrumentation and Methods for Astrophysics Machine Learning

Abstract

We develop the use of mutual information (MI), a well-established metric in information theory, to interpret the inner workings of deep learning models. To accurately estimate MI from a finite number of samples, we present GMM-MI (pronounced ``Jimmie""), an algorithm based on Gaussian mixture models that can be applied to both discrete and continuous settings. GMM-MI is computationally efficient, robust to the choice of hyperparameters and provides the uncertainty on the MI estimate due to the finite sample size. We extensively validate GMM-MI on toy data for which the ground truth MI is known, comparing its performance against established mutual information estimators. We then demonstrate the use of our MI estimator in the context of representation learning, working with synthetic data and physical datasets describing highly non-linear processes. We train deep learning models to encode high-dimensional data within a meaningful compressed (latent) representation, and use GMM-MI to quantify both the level of disentanglement between the latent variables, and their association with relevant physical quantities, thus unlocking the interpretability of the latent representation. We make GMM-MI publicly available.

Keywords

Cite

@article{arxiv.2211.00024,
  title  = {A robust estimator of mutual information for deep learning interpretability},
  author = {Davide Piras and Hiranya V. Peiris and Andrew Pontzen and Luisa Lucie-Smith and Ningyuan Guo and Brian Nord},
  journal= {arXiv preprint arXiv:2211.00024},
  year   = {2023}
}

Comments

30 pages, 8 figures. Minor changes to match version accepted for publication in Machine Learning: Science and Technology. GMM-MI available at https://github.com/dpiras/GMM-MI

R2 v1 2026-06-28T04:52:44.464Z