Saved in:
Bibliographic Details
Main Authors: Hilaire, Baptiste, Karystinaios, Emmanouil, Widmer, Gerhard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.26521
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Interpretability is essential for deploying deep learning models in symbolic music analysis, yet most research emphasizes model performance over explanation. To address this, we introduce MUSE-Explainer, a new method that helps reveal how music Graph Neural Network models make decisions by providing clear, human-friendly explanations. Our approach generates counterfactual explanations by making small, meaningful changes to musical score graphs that alter a model's prediction while ensuring the results remain musically coherent. Unlike existing methods, MUSE-Explainer tailors its explanations to the structure of musical data and avoids unrealistic or confusing outputs. We evaluate our method on a music analysis task and show it offers intuitive insights that can be visualized with standard music tools such as Verovio.