Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification
2026-04-09 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors studied how different time series classification (TSC) methods perform not just in accuracy but also in energy use. They created a framework to measure the trade-off between prediction quality and resource consumption and introduced a new prunable model called Hydrant. Testing over many datasets and setups, they found that pruning can cut energy use by up to 80% with only a small accuracy loss. Their work helps make TSC methods more efficient and reproducible.
time series classificationenergy efficiencypruningpredictive performancehardware evaluationhybrid classifiersHydraQuantmodel pruning
Authors
Raphael Fischer, Angus Dempster, Sebastian Buschjäger, Matthias Jakobs, Urav Maniar, Geoffrey I. Webb
Abstract
Time series classification (TSC) enables important use cases, however lacks a unified understanding of performance trade-offs across models, datasets, and hardware. While resource awareness has grown in the field, TSC methods have not yet been rigorously evaluated for energy efficiency. This paper introduces a holistic evaluation framework that explicitly explores the balance of predictive performance and resource consumption in TSC. To boost efficiency, we apply a theoretically bounded pruning strategy to leading hybrid classifiers - Hydra and Quant - and present Hydrant, a novel, prunable combination of both. With over 4000 experimental configurations across 20 MONSTER datasets, 13 methods, and three compute setups, we systematically analyze how model design, hyperparameters, and hardware choices affect practical TSC performance. Our results showcase that pruning can significantly reduce energy consumption by up to 80% while maintaining competitive predictive quality, usually costing the model less than 5% of accuracy. The proposed methodology, experimental results, and accompanying software advance TSC toward sustainable and reproducible practice.