EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming
About
Time series classification is an important analytical task across diverse domains. However, its practical application is often hindered by the scarcity of labeled data and the requirement for substantial computational resources. To address these challenges, this paper proposes EvoTSC, a novel genetic programming approach designed to automatically evolve lightweight feature learning models for time series classification. The core of EvoTSC is a carefully designed multi-layer program structure that strategically embeds diverse forms of prior expert knowledge into the evolutionary process, effectively guiding the search toward operations known to be highly effective for time series analysis. To mitigate the common overfitting problem in time series classification, a tailored Pareto tournament selection strategy is proposed to favor models that perform consistently well across varying training data subsets, promoting the discovery of highly generalizable models. Extensive experiments conducted on univariate time series classification datasets demonstrate that EvoTSC significantly outperforms eleven benchmark methods in most comparisons. Further analyses verify the contribution of each component and the resource efficiency of the evolved models.
Key insights
What problem does EvoTSC solve?
EvoTSC uses genetic programming to automatically evolve lightweight, interpretable feature learning models for univariate time series classification, addressing high computational cost and black-box opacity of neural network methods.
How does it differ from prior work?
Unlike fixed hand-crafted features or large neural networks, EvoTSC uses a multi-layer program structure with a Pareto tournament selection. On 86 UCR datasets, it wins on 71 of 86 against catch22 and 42 against SoftCLT.
What are the practical uses?
EvoTSC targets resource-constrained environments like wearable health devices. On ECG5000, evolved models need roughly 10^4 FLOPs and kilobytes of memory, fitting within STM32 microcontroller limits, unlike neural network baselines.
What limitations do the authors note?
The authors state EvoTSC handles only equal-length univariate series. Future work includes extending to multivariate series with cross-variate dependencies and transferring evolved subtree structures across datasets.