Expert-Transformer with Prototype-Aware Contrastive Learning for Semi-Supervised Time-Series Classification
Electronics · 26.05.2026 · 15 (11) · 2303
DOI: 10.3390/electronics15112303 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 26.05.2026. Verfasst von Zhen Huang und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Grid Corporation of China.
Abstract (Originalsprache)
Semi-supervised time-series classification (TSC) faces challenges in handling intra-class variability and distribution shifts, which limit the effectiveness of standard contrastive learning methods. To address these limitations, we propose the Expert-Transformer with Prototype-Aware Contrastive Learning (ExT-PACL), a novel framework that integrates an uncertainty-guided Mixture-of-Experts (MoE) module within a Transformer encoder to dynamically capture diverse temporal patterns. An expert balancing strategy ensures all experts contribute meaningfully, preventing collapse and enhancing representation robustness. In addition, a prototype-aware contrastive learning loss guides both labeled and high-confidence unlabeled samples toward class prototypes, improving discriminative power and reducing reliance on large negative sample sets. Extensive experiments on multiple benchmark datasets demonstrate that ExT-PACL achieves superior generalization and state-of-the-art performance.
Förderung
- State Grid Corporation of China
Zitieren
APA
Huang, Z., Peng, F., Hou, K., Xia, D., & An, T. (2026). Expert-Transformer with Prototype-Aware Contrastive Learning for Semi-Supervised Time-Series Classification. Electronics, 15(11), 2303. https://doi.org/10.3390/electronics15112303
Vancouver
Huang Z, Peng F, Hou K, Xia D, An T. Expert-Transformer with Prototype-Aware Contrastive Learning for Semi-Supervised Time-Series Classification. Electronics. 2026;15(11):2303. doi:10.3390/electronics15112303
BibTeX
@article{Huang2026,
author = {Huang, Zhen and Peng, Fei and Hou, Kaiyuan and Xia, Deming and An, Tianyu},
title = {Expert-Transformer with Prototype-Aware Contrastive Learning for Semi-Supervised Time-Series Classification},
journal = {Electronics},
year = {2026},
volume = {15},
number = {11},
pages = {2303},
doi = {10.3390/electronics15112303}
}
EUVIMED