# Music102: An D12-equivariant transformer for chord progression accompaniment

arXiv: https://arxiv.org/abs/2410.18151 · HTML: https://mlsanity.com/paper/2410.18151/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs](https://mlsanity.com/paper/2206.11990/) (2022)
- [EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations](https://mlsanity.com/paper/2306.12059/) (2023)
- [e3nn: Euclidean Neural Networks](https://mlsanity.com/paper/2207.09453/) (2022)
- [POP909: A Pop-song Dataset for Music Arrangement Generation](https://mlsanity.com/paper/2008.07142/) (2020)
- [Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation](https://mlsanity.com/paper/2210.10349/) (2022)
- [PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective](https://mlsanity.com/paper/2309.02265/) (2023)
- [Toward Fully Self-Supervised Multi-Pitch Estimation](https://mlsanity.com/paper/2402.15569/) (2024)
- [Learning the helix topology of musical pitch](https://mlsanity.com/paper/1910.10246/) (2019)
- [Deep rank-based transposition-invariant distances on musical sequences](https://mlsanity.com/paper/1709.00740/) (2017)

## Built on by (most cited first, 1 of 1)

- [Equivariant Music Transformer](https://mlsanity.com/paper/2608.03920/) (2026)

## Abstract (arXiv)

We present Music102, an advanced model aimed at enhancing chord progression accompaniment through a D12-equivariant transformer. Inspired by group theory and symbolic music structures, Music102 leverages musical symmetry--such as transposition and reflection operations--integrating these properties into the transformer architecture. By encoding prior music knowledge, the model maintains equivariance across both melody and chord sequences. The POP909 dataset was employed to train and evaluate Music102, revealing significant improvements over the non-equivariant Music101 prototype Music101 in both weighted loss and exact accuracy metrics, despite using fewer parameters. This work showcases the adaptability of self-attention mechanisms and layer normalization to the discrete musical domain, addressing challenges in computational music analysis. With its stable and flexible neural framework, Music102 sets the stage for further exploration in equivariant music generation and computational composition tools, bridging mathematical theory with practical music performance.