Metraipolis › archive › dc_6fe78bce09e1

SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning — arXiv:2609.32676

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32676
License (as archived)
CC0-1.0
Archived
2026-10-07T22:36:45.675Z
SHA-256 of the archived text
8d0ed8b9b906bebc075096a2980a6ea6a7478c33548a8b433a99d6c518e73282
Stable URL of this page
https://metraipolis.com/documento/dc_6fe78bce09e1

How to cite

SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning — arXiv:2609.32676 — arXiv (en), https://arxiv.org/abs/2609.32676 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fe78bce09e1 (Metraipolis archive dc_6fe78bce09e1, sha256 8d0ed8b9b906bebc075096a2980a6ea6a7478c33548a8b433a99d6c518e73282)
BibTeX
@misc{dc6fe78bce09e1,
  title = {SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning — arXiv:2609.32676},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32676},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fe78bce09e1; sha256 8d0ed8b9b906bebc075096a2980a6ea6a7478c33548a8b433a99d6c518e73282},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32676. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Time Series Foundation Models (TSFMs) have achieved remarkable zero-shot performance through extensive pre-training on massive time series datasets. Nevertheless, due to the low-dimensional properties and diverse structural patterns of time series data, performing naive fine-tuning on TSFMs often leads to overfitting and falling into the mean-prediction trap. To address these challenges, we propose SIFT, a robust adaptation method that enhances time series foundation models by preserving Semantic Invariance and structural Fidelity throughout the fine-Tuning process. We employ semantic-invariant adversarial augmentation, which utilizes semantic spectrum decomposition to partition the semantic space and then generates perturbations within the non-core semantic subspace to bolster the model's robustness against these perturbations, mitigating overfitting. We implement a component-based structural fidelity enhancement, which facilitates component-wise mixup and imposes a reconstruction objective to improve the model's ability to preserve structural fidelity, alleviating the mean-prediction trap. Extensive experiments on representative TSFMs covering 10 real-world datasets demonstrate that SIFT can significantly enhance the performance of TSFMs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.32676 — 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 2026-10-07T22:14:27.740Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).