AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation

2025-12-20

AI Summary

This study addresses the inefficiency and non-computability of manual Schenkerian analysis in hierarchical music analysis of Baroque fugue subjects. We propose the first end-to-end, automated hierarchical analysis framework for multi-relational music graphs. Methodologically, we introduce a novel differentiable graph pooling mechanism based on node isolation, integrated with multi-relational graph representation learning and a hierarchical graph neural network, enabling joint learning from note-level inputs to structural-level representations. Evaluated on a fugue subject dataset, our model achieves expert-level analytical accuracy while substantially improving efficiency, consistency, and reproducibility. The learned hierarchical representations are semantically grounded and computationally tractable, providing an interpretable and scalable structural foundation for downstream tasks—including music understanding, generation, and pedagogy.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Hierarchical representations provide powerful and principled approaches for analyzing many musical genres. Such representations have been broadly studied in music theory, for instance via Schenkerian analysis (SchA). Hierarchical music analyses, however, are highly cost-intensive; the analysis of a single piece of music requires a great deal of time and effort from trained experts. The representation of hierarchical analyses in a computer-readable format is a further challenge. Given recent developments in hierarchical deep learning and increasing quantities of computer-readable data, there is great promise in extending such work for an automatic hierarchical representation framework. This paper thus introduces a novel approach, AutoSchA, which extends recent developments in graph neural networks (GNNs) for hierarchical music analysis. AutoSchA features three key contributions: 1) a new graph learning framework for hierarchical music representation, 2) a new graph pooling mechanism based on node isolation that directly optimizes learned pooling assignments, and 3) a state-of-the-art architecture that integrates such developments for automatic hierarchical music analysis. We show, in a suite of experiments, that AutoSchA performs comparably to human experts when analyzing Baroque fugue subjects.

Problem

• Automates hierarchical music analysis to reduce expert time
• Creates computer-readable hierarchical music representations
• Uses graph neural networks for automatic Schenkerian-style analysis

Innovation

• Graph neural networks for hierarchical music analysis
• Node isolation based graph pooling mechanism
• Automatic framework for music representation learning