Large-Scale Training Data Attribution for Music Generative Models via Unlearning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911194525204480 |
|---|---|
| author | Choi, Woosung Koo, Junghyun Cheuk, Kin Wai Serrà, Joan Martínez-Ramírez, Marco A. Ikemiya, Yukara Murata, Naoki Takida, Yuhta Liao, Wei-Hsiang Mitsufuji, Yuki |
| author_facet | Choi, Woosung Koo, Junghyun Cheuk, Kin Wai Serrà, Joan Martínez-Ramírez, Marco A. Ikemiya, Yukara Murata, Naoki Takida, Yuhta Liao, Wei-Hsiang Mitsufuji, Yuki |
| contents | This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the generation of a particular output from a specific model. This is crucial in the context of AI-generated music, where proper recognition and credit for original artists are generally overlooked. By enabling white-box attribution, our work supports a fairer system for acknowledging artistic contributions and addresses pressing concerns related to AI ethics and copyright. We apply unlearning-based attribution to a text-to-music diffusion model trained on a large-scale dataset and investigate its feasibility and behavior in this setting. To validate the method, we perform a grid search over different hyperparameter configurations and quantitatively evaluate the consistency of the unlearning approach. We then compare attribution patterns from unlearning with non-counterfactual approaches. Our findings suggest that unlearning-based approaches can be effectively adapted to music generative models, introducing large-scale TDA to this domain and paving the way for more ethical and accountable AI systems for music creation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18312 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Large-Scale Training Data Attribution for Music Generative Models via Unlearning Choi, Woosung Koo, Junghyun Cheuk, Kin Wai Serrà, Joan Martínez-Ramírez, Marco A. Ikemiya, Yukara Murata, Naoki Takida, Yuhta Liao, Wei-Hsiang Mitsufuji, Yuki Sound Audio and Speech Processing This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the generation of a particular output from a specific model. This is crucial in the context of AI-generated music, where proper recognition and credit for original artists are generally overlooked. By enabling white-box attribution, our work supports a fairer system for acknowledging artistic contributions and addresses pressing concerns related to AI ethics and copyright. We apply unlearning-based attribution to a text-to-music diffusion model trained on a large-scale dataset and investigate its feasibility and behavior in this setting. To validate the method, we perform a grid search over different hyperparameter configurations and quantitatively evaluate the consistency of the unlearning approach. We then compare attribution patterns from unlearning with non-counterfactual approaches. Our findings suggest that unlearning-based approaches can be effectively adapted to music generative models, introducing large-scale TDA to this domain and paving the way for more ethical and accountable AI systems for music creation. |
| title | Large-Scale Training Data Attribution for Music Generative Models via Unlearning |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2506.18312 |