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

• URL: http://arxiv.org/abs/2509.26521v1
• Date: Tue, 30 Sep 2025 16:58:07 GMT
• Title: MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models
• Authors: Baptiste Hilaire, Emmanouil Karystinaios, Gerhard Widmer,
• Abstract summary: We introduce MUSE-Explainer, a new method that helps reveal how music Graph Neural Network models make decisions by providing clear, human-friendly explanations.<n>Our approach generates counterfactual explanations by making small, meaningful changes to musical score graphs.<n>Unlike existing methods, MUSE-Explainer tailors its explanations to the structure of musical data and avoids unrealistic or confusing outputs.
• Score: 8.936641769532693
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning [69.78158549955384]
  We introduce a novel approach that treats core music theory rules, such as those governing beats and intervals, as programmatic functions.<n>This approach generates verifiable sheet music questions in both textual and visual modalities.<n> Evaluation results on SSMR-Bench highlight the key role reasoning plays in interpreting sheet music.
  arXiv  Detail & Related papers  (2025-09-04T09:42:17Z)
• A constraints-based approach to fully interpretable neural networks for detecting learner behaviors [0.6138671548064356]
  We describe a novel approach to creating a neural-network-based behavior detection model that is interpretable by design.<n>Our model is fully interpretable, meaning that the parameters we extract for our explanations have a clear interpretation.<n>We train the model to detect gaming-the-system behavior, evaluate its performance on this task, and compare its learned patterns to those identified by human experts.
  arXiv  Detail & Related papers  (2025-04-10T16:58:11Z)
• Towards Explainable and Interpretable Musical Difficulty Estimation: A Parameter-efficient Approach [49.2787113554916]
  Estimating music piece difficulty is important for organizing educational music collections. Our work employs explainable descriptors for difficulty estimation in symbolic music representations. Our approach, evaluated in piano repertoire categorized in 9 classes, achieved 41.4% accuracy independently, with a mean squared error (MSE) of 1.7.
  arXiv  Detail & Related papers  (2024-08-01T11:23:42Z)
• Combinatorial music generation model with song structure graph analysis [18.71152526968065]
  We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note sequences acts as the edge feature. We trained a Graph Neural Network to obtain node representation in the graph, then we use node representation as input of Unet to generate CONLON pianoroll image latent.
  arXiv  Detail & Related papers  (2023-12-24T04:09:30Z)
• Evaluating the Utility of Model Explanations for Model Development [54.23538543168767]
  We evaluate whether explanations can improve human decision-making in practical scenarios of machine learning model development. To our surprise, we did not find evidence of significant improvement on tasks when users were provided with any of the saliency maps. These findings suggest caution regarding the usefulness and potential for misunderstanding in saliency-based explanations.
  arXiv  Detail & Related papers  (2023-12-10T23:13:23Z)
• Motif-Centric Representation Learning for Symbolic Music [5.781931021964343]
  We learn the implicit relationship between motifs and their variations via representation learning. A regularization-based method, VICReg, is adopted for pretraining, while contrastive learning is used for fine-tuning. We visualize the acquired motif representations, offering an intuitive comprehension of the overall structure of a music piece.
  arXiv  Detail & Related papers  (2023-09-19T13:09:03Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities [6.832341432995627]
  Music emotion recognition is an important task in MIR (Music Information Retrieval) research. One important step towards better models would be to understand what a model is actually learning from the data. We show how to derive explanations of model predictions in terms of spectrogram image segments that connect to the high-level emotion prediction.
  arXiv  Detail & Related papers  (2021-06-14T22:49:19Z)
• Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations [64.85696493596821]
  In computer vision applications, generative counterfactual methods indicate how to perturb a model's input to change its prediction. We propose a counterfactual method that learns a perturbation in a disentangled latent space that is constrained using a diversity-enforcing loss. Our model improves the success rate of producing high-quality valuable explanations when compared to previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-03-18T12:57:34Z)
• Deducing neighborhoods of classes from a fitted model [68.8204255655161]
  In this article a new kind of interpretable machine learning method is presented. It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts. Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
  arXiv  Detail & Related papers  (2020-09-11T16:35:53Z)
• ViCE: Visual Counterfactual Explanations for Machine Learning Models [13.94542147252982]
  We present an interactive visual analytics tool, ViCE, that generates counterfactual explanations to contextualize and evaluate model decisions. Results are effectively displayed in a visual interface where counterfactual explanations are highlighted and interactive methods are provided for users to explore the data and model.
  arXiv  Detail & Related papers  (2020-03-05T04:43:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.