2025/09/30 by Hilaire, Baptiste, Karystinaios, Emmanouil, Widmer, Gerhard
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Sound (cs.SD)
paper · doi:10.48550/arxiv.2509.26521
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.