Graph Neural Networks

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis
Introduces ProGress, a hybrid symbolic music generation model combining graph diffusion and Schenkerian analysis for interpretable, structured, and musically coherent outputs. Accepted at NeurIPS 2025 (Creative AI Track).
Stephen Ni-Hahn, Chao Péter Yang, Mingchen Ma, Cynthia Rudin, Simon Mak, Yue Jiang
Code
SchenkerLink: Human-in-the-Loop Hierarchical Music Analysis with Uncertainty-Aware Graph Link Prediction
SchenkerLink introduces an uncertainty-aware, human-in-the-loop framework for hierarchical music analysis with graph link prediction, supporting interpretable, collaborative analysis. Under review for CHI ’26.
Stephen Ni-Hahn, Jerry Zhu, Chao Péter Yang, Cynthia Rudin, Simon Mak, Yue Jiang