MSNet and LS-Net: Scalable Multi-Scale Multi-Representation Networks for Time Series Classification

Abstract

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: MSNet, a hierarchical multi-scale convolutional network optimized for robustness and calibration, and LS-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 analysis confirms statistically significant performance differences among the top models. Results show that LiteMV achieves the highest mean accuracy, MSNet provides superior probabilistic calibration (lowest NLL), and LS-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 MSNet and LS-Net is available at: https://github.com/alagoz/msnet-lsnet-tsc

Figures (5)

• Figure 1: Architecture comparison of the proposed models. MSNet employs three multi-scale convolution branches ($k=3,5,7$) followed by a feature fusion block. LS-Net uses a lightweight two-branch design and incorporates a confidence-based early-exit mechanism to reduce inference cost.
• Figure 2: CD diagram based on accuracy rankings across 142 datasets. Lower ranks indicate better performance. Methods connected by a horizontal bar are not significantly different according to the Nemenyi test.
• Figure 3: Multi comparision matrix.
• Figure 4: Pareto tradeoff between mean training time and classification accuracy. Marker size represents mean AUC, while color encodes mean NLL. The dashed curve denotes the Pareto frontier, identifying models that achieve optimal tradeoffs between predictive performance and computational cost.
• Figure 5: Accuracy versus mean NLL across evaluated architectures.