TypiCore: A Hybrid Active Query Strategy for Class-Incremental Learning on Time Series
2026-07-20 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors study how to teach computer models to recognize new categories in time-based data when only a limited number of labeled examples can be asked for, which is common in real life. They test many methods for picking which examples to label and find that usual approaches relying on uncertainty or distribution don’t work well with tight labeling limits. To improve this, they create a new method called TypiCore that smartly picks examples based on how typical and diverse they are, leading to better learning results. Their tests show TypiCore can perform as well or better than methods that use all labels while using much fewer annotations.
Time seriesContinual LearningActive LearningClass-Incremental LearningMultivariate time seriesLabel efficiencyQuery strategiesRehearsal methodsDistribution shiftAnnotation budget
Authors
Gabor Szucs, Samuel Jacsev, Marcell Nemeth, Davide Dalle Pezze, Gian Antonio Susto
Abstract
Time series data play a pivotal role across numerous domains, including healthcare and manufacturing. In real-world environments, models must cope with distribution shifts over time, a challenge commonly addressed through Continual Learning (CL) techniques. However, existing CL methods face a critical limitation: real-world data streams are rarely fully labeled, making annotation cost a major practical constraint. This paper investigates Active Class-Incremental Learning (ACIL) for multivariate time series, where a model must sequentially learn new classes while selectively querying labels under a fixed annotation budget. We present a systematic evaluation of a wide range of query strategies combined with multiple rehearsal-based approaches, assessing their impact on plasticity, stability, and label efficiency across four benchmark datasets. Our analysis reveals the limitations of uncertainty-based and distribution-aware methods in achieving strong performance under constrained labeling budgets. To address these shortcomings, we propose TypiCore, a novel hybrid query strategy that alternates between typicality-based and diversity-based sample selection across active learning cycles, enabling the construction of memory buffers that are both representative and diverse. Evaluated on the TSCIL benchmark, TypiCore delivers statistically significant improvements over all baselines and matches or surpasses fully supervised continual learning performance on multiple datasets while requiring a fraction of the available labels.