Metraipolis › archive › dc_830d33e2621f
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models — arXiv:2608.30081
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30081
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:37:02.111Z
- SHA-256 of the archived text
16863b0b1fd97cde5ebb84fcb6bad4e1b7473ae2d0e7ef0de4a1bfdc2924d07c- Stable URL of this page
https://metraipolis.com/documento/dc_830d33e2621f
How to cite
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models — arXiv:2608.30081 — arXiv (en), https://arxiv.org/abs/2608.30081 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_830d33e2621f (Metraipolis archive dc_830d33e2621f, sha256 16863b0b1fd97cde5ebb84fcb6bad4e1b7473ae2d0e7ef0de4a1bfdc2924d07c)
BibTeX
@misc{dc830d33e2621f,
title = {Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models — arXiv:2608.30081},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30081},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_830d33e2621f; sha256 16863b0b1fd97cde5ebb84fcb6bad4e1b7473ae2d0e7ef0de4a1bfdc2924d07c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30081. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding which training samples influence a generated image is an important problem in generative modeling. In flow matching, training samples influence the generated image through the velocity field along the generation trajectory. Removing samples to examine their counterfactual influence changes the velocity field, and the resulting effect on the final image depends on how the change propagates through the trajectory. Consequently, local changes in the velocity field do not necessarily predict the final counterfactual effect. This work investigates attribution in flow-matching models through a hybrid analytical--learned approach, and uses it to derive trajectory-based attribution scores at the cluster level. We evaluate these attribution scores using independently retrained leave-one-cluster-out (LOCO) models, and compare with several attribution baselines using two different flow-matching latent spaces. Our experiments show that semantic similarity constitutes a strong baseline, while the closed-form trajectory-based attribution is competitive in some metrics without requiring counterfactual retraining or model gradients. Our results show that attribution in flow matching depends not only on semantic similarity to training samples, but also on the latent representation, trajectory dynamics, and how influence is propagated to the final output. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.30081 — 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 2026-10-17T08:13:26.788Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).