Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915827062669312 |
|---|---|
| author | Yi, Yungang Li, Weihua Kuo, Matthew Shi, Catherine Bai, Quan |
| author_facet | Yi, Yungang Li, Weihua Kuo, Matthew Shi, Catherine Bai, Quan |
| contents | Long-context modeling is essential for symbolic music generation, since motif repetition and developmental variation can span thousands of musical events, yet practical workflows frequently rely on resource-limited hardware. We introduce Depth-Structured Music Recurrence (DSMR), a training-time design that learns from complete compositions end to end by streaming each piece left-to-right with stateful recurrent attention and distributing layer-wise memory horizons under a fixed recurrent-state budget. Our main instantiation, two-scale DSMR, assigns long history windows to lower layers and a uniform short window to the remaining layers. On the MAESTRO piano performance dataset, two-scale DSMR matches a full-memory recurrent reference in perplexity (5.96 vs. 5.98) while using approximately 59% less GPU memory and achieving roughly 36% higher throughput. Variant analyses further show strong layer substitutability under binary-horizon schedules: performance depends primarily on total allocated memory rather than which layers carry it. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19816 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling Yi, Yungang Li, Weihua Kuo, Matthew Shi, Catherine Bai, Quan Sound Artificial Intelligence Machine Learning Long-context modeling is essential for symbolic music generation, since motif repetition and developmental variation can span thousands of musical events, yet practical workflows frequently rely on resource-limited hardware. We introduce Depth-Structured Music Recurrence (DSMR), a training-time design that learns from complete compositions end to end by streaming each piece left-to-right with stateful recurrent attention and distributing layer-wise memory horizons under a fixed recurrent-state budget. Our main instantiation, two-scale DSMR, assigns long history windows to lower layers and a uniform short window to the remaining layers. On the MAESTRO piano performance dataset, two-scale DSMR matches a full-memory recurrent reference in perplexity (5.96 vs. 5.98) while using approximately 59% less GPU memory and achieving roughly 36% higher throughput. Variant analyses further show strong layer substitutability under binary-horizon schedules: performance depends primarily on total allocated memory rather than which layers carry it. |
| title | Depth-Structured Music Recurrence: Budgeted Recurrent Attention for Full-Piece Symbolic Music Modeling |
| topic | Sound Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.19816 |