让音乐图神经网络的决策过程可解释，通过合理修改乐谱生成直观反事实说明。
MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models
- 基于乐谱图结构生成小幅度改动的反事实解释。
- 修改后模型预测改变且乐理上依然合理，避免不自然输出。
- 结果可用标准乐谱工具可视化，适合音乐学者与创作者使用。
可解释性对符号音乐分析中的深度学习模型部署至关重要，但现有研究多关注模型性能而忽视解释。为此，我们提出 MUSE-Explainer，一种新方法，通过在音乐图上进行小而有意义的修改，生成能改变模型预测且保持音乐连贯性的反事实解释，从而揭示图神经网络的决策机制。该方法针对音乐数据结构特性设计，避免产生不现实或令人困惑的结果。我们在一项音乐分析任务上评估该方法，结果显示其能提供直观可理解的解释，并可通过 Verovio 等标准音乐工具进行可视化。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。