Metraipolis › archive › dc_b7cd42b32cd2

CADENCE: A Confidence-Adaptive Dual-Expert Network for Fast and Accurate Time Series Classification — arXiv:2609.35929

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35929
License (as archived)
CC0-1.0
Archived
2026-10-07T17:28:36.103Z
SHA-256 of the archived text
bb1ad9c33290a3b6d457ae9f777eae2d40a1ecdf72905e574da25dae1a012b15
Stable URL of this page
https://metraipolis.com/documento/dc_b7cd42b32cd2

How to cite

CADENCE: A Confidence-Adaptive Dual-Expert Network for Fast and Accurate Time Series Classification — arXiv:2609.35929 — arXiv (en), https://arxiv.org/abs/2609.35929 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7cd42b32cd2 (Metraipolis archive dc_b7cd42b32cd2, sha256 bb1ad9c33290a3b6d457ae9f777eae2d40a1ecdf72905e574da25dae1a012b15)
BibTeX
@misc{dcb7cd42b32cd2,
  title = {CADENCE: A Confidence-Adaptive Dual-Expert Network for Fast and Accurate Time Series Classification — arXiv:2609.35929},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35929},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7cd42b32cd2; sha256 bb1ad9c33290a3b6d457ae9f777eae2d40a1ecdf72905e574da25dae1a012b15},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35929. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Time series classification (TSC) exhibits a sharp trade-off between accuracy and computational scalability. Meta-ensembles like HIVE-COTE 2.0 reach state-of-the-art accuracy but require extensive compute, whereas ultra-fast random convolutional transforms (e.g., MiniRocket, Hydra) run in seconds but struggle with phase-independent distributions, signal kinematics, and decision tree fragmentation on large class counts. In this work, we present CADENCE (Confidence-Adaptive Dual-Expert Network for time series Classification Excellence), a unified, CPU-native dual-expert architecture. CADENCE decouples representation learning into two specialized pathways: (i) a Convolutional Linear Expert pairing 10,000 deterministic dilated features with closed-form L2-regularized Woodbury ridge classification, and (ii) a Distributional Interval Expert pairing competing dilated kernels (Hydra) with dyadic Cornish-Fisher moment approximations across signal kinematics and FFT spectral bands, fitted with an ExtraTrees ensemble. An internal validation meta-router with rare-class preservation dynamically selects between pure expert routing and confidence-weighted soft blending, followed by a full refit on 100% of training data. Evaluated across all 109 equal-length UCR Archive datasets over 30 resamples (3,270 total runs), CADENCE achieves a grand mean accuracy of 0.8864. This ranks #2 across the archive, surpassed only by HIVE-COTE 2.0 (0.8895, p_Holm = 0.295, no statistically significant difference), while outperforming Hydra+MultiRocket (0.8818), MultiRocket (0.8797), and HIVE-COTE 1.0 (0.8786, p_Holm = 0.048). CADENCE closes the gap to HIVE-COTE 2.0 to 0.31 percentage points while taking an average of only 17.53 seconds per dataset on a dual-core CPU. Source code and evaluation scripts: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35929 — 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 2026-10-07T16:59:48.081Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).