Saved in:
| Main Authors: | , , |
|---|---|
| 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!
|
| _version_ | 1866912618522869760 |
|---|---|
| author | Hilaire, Baptiste Karystinaios, Emmanouil Widmer, Gerhard |
| author_facet | Hilaire, Baptiste Karystinaios, Emmanouil Widmer, Gerhard |
| 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26521 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models Hilaire, Baptiste Karystinaios, Emmanouil Widmer, Gerhard Sound Artificial Intelligence 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. |
| title | MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2509.26521 |