Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation

2026-09-07

AI Summary

本文提出一种针对多变量时间序列分类的类特定维度选择框架，通过独立识别每类信息维度并融合模型来提高分类性能和特征表示质量。

Abstract

In this paper, we propose a class-wise dimension (channel) selection framework for Multivariate Time Series Classification (MTSC). Rather than applying a single global dimension selection process, the proposed approach independently identifies informative dimensions for each class. A dedicated learning process is subsequently performed for each class, followed by a fusion stage for final prediction. The objective is to improve the generation of discriminative feature representations while reducing the influence of noisy or non-informative dimensions. The proposed framework is evaluated using MiniRocket, a random kernel-based baseline method. Experimental results indicate that class-wise dimension selection improves the quality of extracted representations and can enhance classification performance, particularly in high-dimensional settings. These findings suggest that incorporating class-specific information into the training process represents a promising direction for MTSC, improving robustness through consistent gains across heterogeneous datasets, and interpretability through the explicit identification of class-relevant dimensions.

Problem

• Multivariate Time Series Classification
• discriminative feature representations
• noisy dimensions
• non-informative dimensions
• class-wise dimension selection

Innovation

• class-wise dimension selection
• Multivariate Time Series Classification (MTSC)
• feature representation
• dimension reduction
• classification performance