多表示多尺度网络提升时间序列分类性能，兼顾准确率、校准度与效率。
MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification
- 融合多种时间序列表示，通过多尺度卷积统一建模。
- 在142个数据集上验证，最高平均准确率达92.3%，校准最优（最低NLL）。
- 提供轻量版适合资源受限场景，支持灵活部署于不同需求。
时间序列分类性能不仅依赖于架构设计，还取决于输入表示的多样性。本文提出一种可扩展的多尺度卷积框架，系统整合结构化多表示输入，用于单变量时间序列。引入两种架构：MRMS-Net，一种优化鲁棒性与校准的分层多尺度卷积网络；以及轻量级变体LMRMS-Net，专为高效部署设计。同时，将原用于多变量输入的LiteMV适配至多表示单变量信号，实现跨表示交互。所有模型在142个基准数据集上以统一实验协议评估。关键差异（CD）分析证实顶级模型间存在显著性能差异。结果表明，LiteMV达到最高平均准确率（92.3%），MRMS-Net在概率校准方面表现最优（最低NLL），LMRMS-Net则取得最佳效率-准确率权衡。帕累托分析进一步证明，多表示多尺度建模提供了可调节的设计空间，适用于高精度、强校准或资源受限等不同场景。这些发现确立了可扩展的多表示多尺度学习作为现代时间序列分类的可行且有效方向。参考实现见：https://github.com/alagoz/mrmsnet-tsc
原文摘要 · Abstract (English)
Time series classification (TSC) performance depends not only on architectural design but also on the diversity of input representations. In this work, we propose a scalable multi-scale convolutional framework that systematically integrates structured multi-representation inputs for univariate time series. We introduce two architectures: MRMS-Net, a hierarchical multi-scale convolutional network optimized for robustness and calibration, and LMRMS-Net, a lightweight variant designed for efficiency-aware deployment. In addition, we adapt LiteMV -- originally developed for multivariate inputs -- to operate on multi-representation univariate signals, enabling cross-representation interaction. We evaluate all models across 142 benchmark datasets under a unified experimental protocol. Critical Difference (CD) analysis confirms statistically significant performance differences among the top models. Results show that LiteMV achieves the highest mean accuracy, MRMS-Net provides superior probabilistic calibration (lowest NLL), and LMRMS-Net offers the best efficiency-accuracy tradeoff. Pareto analysis further demonstrates that multi-representation multi-scale modeling yields a flexible design space that can be tuned for accuracy-oriented, calibration-oriented, or resource-constrained settings. These findings establish scalable multi-representation multi-scale learning as a principled and practical direction for modern TSC. Reference implementation of MRMS-Net and LMRMS-Net is available at: https://github.com/alagoz/mrmsnet-tsc
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。