Physics-Inspired Interpretability Of Machine Learning Models

TL;DR

This paper introduces a physics-inspired method to interpret machine learning models by analyzing their loss landscapes, helping identify key features influencing decisions, which enhances transparency in sensitive AI applications.

Contribution

It proposes a novel approach using energy landscape concepts from physics to identify important input features in machine learning models, a method not previously applied in this context.

Findings

Energy landscape methods can identify relevant features in ML models.

The approach is demonstrated on synthetic and real-world data.

It improves interpretability of complex models.

Abstract

The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous driving. Great interest exists in understanding which features of the input data prompt model decision making. In this contribution, we propose a novel approach to identify relevant features of the input data, inspired by methods from the energy landscapes field, developed in the physical sciences. By identifying conserved weights within groups of minima of the loss landscapes, we can identify the drivers of model decision making. Analogues to this idea exist in the molecular sciences, where coordinate invariants or order parameters are employed to identify critical features of a molecule. However, no such approach exists for machine learning loss landscapes. We will demonstrate the applicability of energy landscape methods to machine learning models and give examples, both synthetic and from the real world, for how these methods can help to make models more interpretable.