mlsanityData to 14 Oct 2026

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

arXiv 2609.35929 ↗First posted 28 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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: https://github.com/onisa-jr/CADENCE.git

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 13 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

8 of 13 references.

References · 8

  1. 2018The UCR Time Series Archivecited by 431
  2. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 387
  3. 2019ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernelscited by 339
  4. 2020MINIROCKET: A Very Fast (Almost) Deterministic Transform for Time Series Classificationcited by 190
  5. 2021HIVE-COTE 2.0: a new meta ensemble for time series classificationcited by 118
  6. 2021MultiRocket: Multiple pooling operators and transformations for fast and effective time series classificationcited by 90
  7. 2019TS-CHIEF: A Scalable and Accurate Forest Algorithm for Time Series Classificationcited by 67
  8. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 54

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing deep learning models for time series classification via knowledge distillation
  2. 2026AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
  3. 2026Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
  4. 2026MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts
  5. 2025FAIM: Frequency-Aware Interactive Mamba for Time Series Classification
  6. 2026AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
  7. 2026EXCODER: EXplainable Classification Of DiscretE time series Representations
  8. 2026End-to-end Early Classification of Time Series in Non-Stationary Environments