Constructing Composite Features for Interpretable Music-Tagging

TL;DR

This paper introduces a genetic programming approach to automatically create interpretable composite features for music tagging, achieving performance comparable to deep learning methods while maintaining transparency.

Contribution

The novel use of genetic programming to evolve interpretable composite features for music tagging enhances performance without sacrificing interpretability.

Findings

Consistent improvements over state-of-the-art systems on MTG-Jamendo and GTZAN datasets.

Effective feature combinations identified within a modest number of GP evaluations.

Top solutions include simple linear, nonlinear, and conditional expressions.

Abstract

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that automatically evolves composite features by mathematically combining base music features, thereby capturing synergistic interactions while preserving interpretability. This approach provides representational benefits similar to deep feature fusion without sacrificing interpretability. Experiments on the MTG-Jamendo and GTZAN datasets demonstrate consistent improvements compared to state-of-the-art systems across base feature sets at different abstraction levels. It should be noted that most of the performance gains are noticed within the first few hundred GP evaluations, indicating that effective feature combinations can be identified under modest search budgets. The top evolved expressions include linear, nonlinear, and conditional forms, with various low-complexity solutions at top performance aligned with parsimony pressure to prefer simpler expressions. Analyzing these composite features further reveals which interactions and transformations tend to be beneficial for tagging, offering insights that remain opaque in black-box deep models.