# Combinatorial music generation model with song structure graph analysis

arXiv: https://arxiv.org/abs/2312.15400 · HTML: https://mlsanity.com/paper/2312.15400/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 24 Dec 2023.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment](https://mlsanity.com/paper/1709.06298/) (2017)
- [Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer](https://mlsanity.com/paper/2111.04093/) (2021)
- [MELONS: generating melody with long-term structure using transformers and structure graph](https://mlsanity.com/paper/2110.05020/) (2021)
- [Cadence Detection in Symbolic Classical Music using Graph Neural Networks](https://mlsanity.com/paper/2208.14819/) (2022)
- [ComMU: Dataset for Combinatorial Music Generation](https://mlsanity.com/paper/2211.09385/) (2022)
- [Symbolic Music Loop Generation with Neural Discrete Representations](https://mlsanity.com/paper/2208.05605/) (2022)
- [Pitchclass2vec: Symbolic Music Structure Segmentation with Chord Embeddings](https://mlsanity.com/paper/2303.15306/) (2023)

## Abstract (arXiv)

In this work, we propose a symbolic music generation model with the song structure graph analysis network. We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note sequences acts as the edge feature. We trained a Graph Neural Network to obtain node representation in the graph, then we use node representation as input of Unet to generate CONLON pianoroll image latent. The outcomes of our experimental results show that the proposed model can generate a comprehensive form of music. Our approach represents a promising and innovative method for symbolic music generation and holds potential applications in various fields in Music Information Retreival, including music composition, music classification, and music inpainting systems.