# MRMS-Net and LMRMS-Net: Scalable Multi-Representation Multi-Scale Networks for Time Series Classification

arXiv: https://arxiv.org/abs/2603.19315 · HTML: https://mlsanity.com/paper/2603.19315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 29 references that are in the map.
- First posted on arXiv 14 Mar 2026.

## Builds on (most cited first, 16 of 16)

- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [HIVE-COTE 2.0: a new meta ensemble for time series classification](https://mlsanity.com/paper/2104.07551/) (2021)
- [Multi-Scale Convolutional Neural Networks for Time Series Classification](https://mlsanity.com/paper/1603.06995/) (2016)
- [MultiRocket: Multiple pooling operators and transformations for fast and effective time series classification](https://mlsanity.com/paper/2102.00457/) (2021)
- [Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification](https://mlsanity.com/paper/2002.10061/) (2020)
- [The FreshPRINCE: A Simple Transformation Based Pipeline Time Series Classifier](https://mlsanity.com/paper/2201.12048/) (2022)
- [ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification](https://mlsanity.com/paper/2405.14608/) (2024)
- [Look Into the LITE in Deep Learning for Time Series Classification](https://mlsanity.com/paper/2409.02869/) (2024)
- [Elastic Similarity and Distance Measures for Multivariate Time Series](https://mlsanity.com/paper/2102.10231/) (2021)
- [Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles](https://mlsanity.com/paper/2602.07579/) (2026)

## Abstract (arXiv)

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