GraphMuse: A Library for Symbolic Music Graph Processing
This work addresses a domain-specific problem for researchers in symbolic music processing by providing a standardized tool, though it is incremental as it builds on existing GNN approaches.
The authors tackled the lack of a unified framework for Graph Neural Networks in symbolic music tasks by developing GraphMuse, a library that improves performance in pitch spelling and cadence detection, achieving significant gains over previous methods.
Graph Neural Networks (GNNs) have recently gained traction in symbolic music tasks, yet a lack of a unified framework impedes progress. Addressing this gap, we present GraphMuse, a graph processing framework and library that facilitates efficient music graph processing and GNN training for symbolic music tasks. Central to our contribution is a new neighbor sampling technique specifically targeted toward meaningful behavior in musical scores. Additionally, GraphMuse integrates hierarchical modeling elements that augment the expressivity and capabilities of graph networks for musical tasks. Experiments with two specific musical prediction tasks -- pitch spelling and cadence detection -- demonstrate significant performance improvement over previous methods. Our hope is that GraphMuse will lead to a boost in, and standardization of, symbolic music processing based on graph representations. The library is available at https://github.com/manoskary/graphmuse