Paper ID: 2302.09949

SpecXAI -- Spectral interpretability of Deep Learning Models

Stefan Druc, Peter Wooldridge, Adarsh Krishnamurthy, Soumik Sarkar, Aditya Balu

Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models. These models, however, are generally regarded as black boxes, which, in spite of their performance, could prevent their use. In this context, the field of eXplainable AI attempts to develop techniques that temper the impenetrable nature of the models and promote a level of understanding of their behavior. Here we present our contribution to XAI methods in the form of a framework that we term SpecXAI, which is based on the spectral characterization of the entire network. We show how this framework can be used to not only understand the network but also manipulate it into a linear interpretable symbolic representation.

Submitted: Feb 20, 2023