# MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models

arXiv: https://arxiv.org/abs/2509.26521 · HTML: https://mlsanity.com/paper/2509.26521/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 12 of 12)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Symbolic Music Representations for Classification Tasks: A Systematic Evaluation](https://mlsanity.com/paper/2309.02567/) (2023)
- [Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier](https://mlsanity.com/paper/2208.12485/) (2022)
- [Cadence Detection in Symbolic Classical Music using Graph Neural Networks](https://mlsanity.com/paper/2208.14819/) (2022)
- [D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion](https://mlsanity.com/paper/2310.19321/) (2023)
- [GraphMuse: A Library for Symbolic Music Graph Processing](https://mlsanity.com/paper/2407.12671/) (2024)
- [SymPAC: Scalable Symbolic Music Generation With Prompts And Constraints](https://mlsanity.com/paper/2409.03055/) (2024)
- [SMUG-Explain: A Framework for Symbolic Music Graph Explanations](https://mlsanity.com/paper/2405.09241/) (2024)

## Abstract (arXiv)

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.