Explainable and Class-Revealing Signal Feature Extraction via Scattering Transform and Constrained Zeroth-Order Optimization

TL;DR

This paper introduces a method combining scattering transform and constrained zeroth-order optimization to extract interpretable features from signal classification models, enhancing understanding of model decisions.

Contribution

It presents a novel approach to interpret scattering transform-based models by optimizing input patterns to reveal class-specific features, addressing the interpretability challenge.

Findings

Effective in synthetic time-series classification tasks

Highlights importance of sparsity and smoothness constraints

Provides insights into feature relevance for classification

Abstract

We propose a new method to extract discriminant and explainable features from a particular machine learning model, i.e., a combination of the scattering transform and the multiclass logistic regression. Although this model is well-known for its ability to learn various signal classes with high classification rate, it remains elusive to understand why it can generate such successful classification, mainly due to the nonlinearity of the scattering transform. In order to uncover the meaning of the scattering transform coefficients selected by the multiclass logistic regression (with the Lasso penalty), we adopt zeroth-order optimization algorithms to search an input pattern that maximizes the class probability of a class of interest given the learned model. In order to do so, it turns out that imposing sparsity and smoothness of input patterns is important. We demonstrate the effectiveness of our proposed method using a couple of synthetic time-series classification problems.