EUVIMEDEUVIMED entdecken
Crossref

Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification

Xin Qin, Mengna Liu, Wenjie Wang, Shuxin Li, Tianjiao Li, Xiufeng Liu, Xu Cheng

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24945-24953

DOI: 10.1609/aaai.v40i29.39682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xin Qin und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Irregular time series (IRTS) are prevalent in real-world applications, where uneven sampling and missing data pose fundamental challenges to deep learning-based feature modeling. Although existing methods attempt to retain timestamp information, they often overlook the structured patterns embedded within the missingness itself, and tend to perform poorly when confronted with class imbalance exacerbated by data incompleteness. Specifically, temporal irregularity hinders the modeling of long-range dependencies and local patterns, while sparse observations limit representational capacity, disproportionately impairing minority classes and leading to severe classification bias. To address these deeply coupled challenges, we propose SPECTRA (Structured Pattern and Enriched Context-aware Temporal Representation Architecture), a unified framework for robust IRTS classification. SPECTRA introduces a frequency-guided observation encoder that reconstructs temporal dependencies in a stable manner, mitigating spectral distortion and information corruption. Complementarily, a missingness pattern encoder explicitly captures the dynamic evolution of missing data and leverages it as a discriminative signal. In addition, a prototype-constrained classification paradigm directly optimizes the geometric structure of the feature space, enhancing intra-class compactness and alleviating generalization bottlenecks caused by class imbalance. Extensive experiments on three public IRTS datasets—P12, P19, and PAM—demonstrate the superior performance of SPECTRA under both missing and imbalanced conditions.

Zitieren

APA

Qin, X., Liu, M., Wang, W., Li, S., Li, T., Liu, X., & Cheng, X. (2026). Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24945-24953. https://doi.org/10.1609/aaai.v40i29.39682

Vancouver

Qin X, Liu M, Wang W, Li S, Li T, Liu X, et al. Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24945-24953. doi:10.1609/aaai.v40i29.39682

BibTeX
@article{Qin2026,
  author = {Qin, Xin and Liu, Mengna and Wang, Wenjie and Li, Shuxin and Li, Tianjiao and Liu, Xiufeng and Cheng, Xu},
  title = {Beyond Missing Data Imputation: Information-Theoretic Coupling of Missingness and Class Imbalance for Optimal Irregular Time Series Classification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {29},
  pages = {24945--24953},
  doi = {10.1609/aaai.v40i29.39682}
}
Kostenlos starten →