# AnalysisGNN: Unified Music Analysis with Graph Neural Networks

arXiv: https://arxiv.org/abs/2509.06654 · HTML: https://mlsanity.com/paper/2509.06654/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Auxiliary Tasks in Multi-task Learning](https://mlsanity.com/paper/1805.06334/) (2018)
- [FAMO: Fast Adaptive Multitask Optimization](https://mlsanity.com/paper/2306.03792/) (2023)
- [Cadence Detection in Symbolic Classical Music using Graph Neural Networks](https://mlsanity.com/paper/2208.14819/) (2022)
- [Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise Features](https://mlsanity.com/paper/2307.03544/) (2023)
- [GraphMuse: A Library for Symbolic Music Graph Processing](https://mlsanity.com/paper/2407.12671/) (2024)
- [Graph-based Polyphonic Multitrack Music Generation](https://mlsanity.com/paper/2307.14928/) (2023)
- [Hierarchical Symbolic Pop Music Generation with Graph Neural Networks](https://mlsanity.com/paper/2409.08155/) (2024)

## Built on by (most cited first, 2 of 2)

- [From Prediction to Collaboration: Interactive Symbolic Music Analysis](https://mlsanity.com/paper/2607.13587/) (2026)
- [ScorePrompts: Natural-Language Exploration of Symbolic Music Scores through Analysis](https://mlsanity.com/paper/2609.13291/) (2026)

## Abstract (arXiv)

Recent years have seen a boom in computational approaches to music analysis, yet each one is typically tailored to a specific analytical domain. In this work, we introduce AnalysisGNN, a novel graph neural network framework that leverages a data-shuffling strategy with a custom weighted multi-task loss and logit fusion between task-specific classifiers to integrate heterogeneously annotated symbolic datasets for comprehensive score analysis. We further integrate a Non-Chord-Tone prediction module, which identifies and excludes passing and non-functional notes from all tasks, thereby improving the consistency of label signals. Experimental evaluations demonstrate that AnalysisGNN achieves performance comparable to traditional static-dataset approaches, while showing increased resilience to domain shifts and annotation inconsistencies across multiple heterogeneous corpora.