PRISM: Lightweight Multivariate Time-Series Classification through Symmetric Multi-Resolution Convolutional Layers

TL;DR

PRISM is a lightweight, fully convolutional multivariate time-series classifier that uses symmetric multi-resolution filters inspired by signal processing, achieving high accuracy with fewer parameters and lower computational cost.

Contribution

It introduces a novel symmetric convolutional module that enforces structural constraints, reducing parameters while maintaining performance in multivariate time series classification.

Findings

PRISM matches or outperforms state-of-the-art models on diverse benchmarks.

PRISM uses significantly fewer parameters and less computation.

The model effectively captures multi-scale temporal dependencies.

Abstract

Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and multi-scale temporal dependencies. Despite recent advances, Transformer and CNN models often remain computationally heavy and rely on many parameters. This work presents PRISM(Per-channel Resolution Informed Symmetric Module), a lightweight fully convolutional classifier. Operating in a channel-independent manner, in its early stage it applies a set of multi-resolution symmetric convolutional filters. This symmetry enforces structural constraints inspired by linear-phase FIR filters from classical signal processing, effectively halving the number of learnable parameters within the initial layers while preserving the full receptive field. Across the diverse UEA multivariate time-series archive as well as specific benchmarks in human activity recognition, sleep staging, and biomedical signals, PRISM matches or outperforms state-of-the-art CNN and Transformer models while using significantly fewer parameters and markedly lower computational cost. By bringing a principled signal processing prior into a modern neural architecture, PRISM offers an effective and computationally economical solution for multivariate time series classification. Code and data are available at https://github.com/fedezuc/PRISM