Physics-Inspired Interpretability Of Machine Learning 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.

6 pages, 2 figures, ICLR 2023 Workshop on Physics for Machine Learning

References in corpus (6)

• Axiomatic Attribution for Deep Networks
• A Survey of Deep Learning Techniques for Autonomous Driving
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Perspective: Energy Landscapes for Machine Learning
• Rethinking the Role of Gradient-Based Attribution Methods for Model Interpretability
• Subaging in underparametrized Deep Neural Networks