Metraipolis › archive › dc_a565f411c4aa
FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization — arXiv:2608.22224
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22224
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:42:42.117Z
- SHA-256 of the archived text
6793b5e04bb0364ec31db338b40eeb96a4c033e14ad92d1e542f40f7a958ca56- Stable URL of this page
https://metraipolis.com/documento/dc_a565f411c4aa
How to cite
FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization — arXiv:2608.22224 — arXiv (en), https://arxiv.org/abs/2608.22224 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a565f411c4aa (Metraipolis archive dc_a565f411c4aa, sha256 6793b5e04bb0364ec31db338b40eeb96a4c033e14ad92d1e542f40f7a958ca56)
BibTeX
@misc{dca565f411c4aa,
title = {FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization — arXiv:2608.22224},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22224},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a565f411c4aa; sha256 6793b5e04bb0364ec31db338b40eeb96a4c033e14ad92d1e542f40f7a958ca56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22224. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal Domain Generalization (TDG) aims to learn from historical domains and generalize to unseen future distributions under concept drift. Nevertheless, prevailing TDG methods struggle with complex real-world streaming scenarios involving both multi-scale drift patterns (e.g., long-term periodicity intertwined with short-term incremental changes) and local uncertainties, especially in continuous settings where observations arrive irregularly. To address this limitation, we propose FreKoo++, a novel continuous spectral-dynamical framework that pioneers the unification of continuous Koopman modal dynamics with adaptive spectral disentanglement. Specifically, FreKoo++ maps source-domain parameters into a compact latent space, modeling their evolution as a superposition of learnable continuous modes where complex eigenvalues jointly encode oscillatory frequency and temporal growth or decay. This formulation naturally accommodates irregular timestamps and supports arbitrary horizon extrapolation without rigid discrete stepping. Furthermore, we propose a new adaptive soft spectral weighting mechanism backed by stability and spectral regularization, which automatically isolates persistent dominant dynamics from transient noise without relying on manual frequency thresholds. We derive modal approximation and generalization bounds that characterize how amplitude and eigenvalue estimation errors propagate with the prediction horizon. Extensive experiments on both discrete and continuous TDG benchmarks demonstrate that FreKoo++ achieves state-of-the-art performance under complex multi-scale drifts and irregular sampling. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22224 — 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 2026-10-18T07:37:52.862Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).