Year: 2025
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Hilaire, Baptiste, Karystinaios, Emmanouil, Widmer, Gerhard
Institution: Johannes Kepler University of Linz
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: H2020 European Research Council
OpenAlex ID: W7084447896
Cites:
Cited by:
Related to: