SMUG-Explain: A Framework for Symbolic Music Graph Explanations

TL;DR

SMUG-Explain is a framework that visualizes how graph neural networks interpret musical scores, aiding understanding of model decisions in tasks like cadence detection.

Contribution

It introduces a novel interactive system for explaining GNN predictions on musical scores with visualizations integrated into music notation.

Findings

Effective visualization of note contributions in musical scores

Application demonstrated on cadence detection in classical music

Open-source implementation available for further use

Abstract

In this work, we present Score MUsic Graph (SMUG)-Explain, a framework for generating and visualizing explanations of graph neural networks applied to arbitrary prediction tasks on musical scores. Our system allows the user to visualize the contribution of input notes (and note features) to the network output, directly in the context of the musical score. We provide an interactive interface based on the music notation engraving library Verovio. We showcase the usage of SMUG-Explain on the task of cadence detection in classical music. All code is available on https://github.com/manoskary/SMUG-Explain.