Metraipolis › archive › dc_01d72a665f06
Functional Dependency beyond Similarity: Hierarchical Decomposition of Training Data Attribution in Music Generative Models — arXiv:2611.08839
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08839
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:37:27.260Z
- SHA-256 of the archived text
56429e82067624cad94a651d1b6bb9eb69b95b2a7d0414ebeb08098797186974- Stable URL of this page
https://metraipolis.com/documento/dc_01d72a665f06
How to cite
Functional Dependency beyond Similarity: Hierarchical Decomposition of Training Data Attribution in Music Generative Models — arXiv:2611.08839 — arXiv (en), https://arxiv.org/abs/2611.08839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01d72a665f06 (Metraipolis archive dc_01d72a665f06, sha256 56429e82067624cad94a651d1b6bb9eb69b95b2a7d0414ebeb08098797186974)
BibTeX
@misc{dc01d72a665f06,
title = {Functional Dependency beyond Similarity: Hierarchical Decomposition of Training Data Attribution in Music Generative Models — arXiv:2611.08839},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08839},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01d72a665f06; sha256 56429e82067624cad94a651d1b6bb9eb69b95b2a7d0414ebeb08098797186974},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Copyright analysis focuses on the similarity between two works. However, generative AI models learn from training data through functional relations beyond similarity. Training Data Attribution (TDA) estimates the influence of each training instance on a generated output and may serve as a basis for remuneration. However, prior studies find global influence, where a few training instances rank as the most influential for almost every generation. Used directly, TDA scores would distribute part of every remuneration to these instances regardless of what was generated. To address this, we propose a new approach in which TDA scores are decomposed into three levels of influence, namely global indicating the influence of a training data to a trained model, group for its influence on a group of generated outputs (that could be clustered together), and specific for its influence on a single generated output. Our study finds that, across several music generative models and TDA methods, global- and group-level influence is non-negligible in every case. Based on these observations, we propose the term functional dependency for the relation of training data to a trained model or to its outputs. This notion both encompasses and distinguishes dependencies of different scopes, allowing TDA scores to be interpreted as distinct forms of contribution in legal, economic and ethical discussions on remuneration. Tema degli esploratori: governance digitale e beni comuni (elenco arXiv cs.CY, nuovi lavori del giorno). Categorie arXiv: Computers and Society (cs.CY) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.08839 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:32:01.921Z dalla pagina https://arxiv.org/list/cs.CY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).