# Meta-Learning for Few-Shot Time Series Classification

arXiv: https://arxiv.org/abs/1909.07155 · HTML: https://mlsanity.com/paper/1909.07155/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2019.

## Built on by (most cited first, 23 of 23)

- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning](https://mlsanity.com/paper/2111.04724/) (2021)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining](https://mlsanity.com/paper/2310.07402/) (2023)
- [Deep Learning for Satellite Image Time Series Analysis: A Review](https://mlsanity.com/paper/2404.03936/) (2024)
- [Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models](https://mlsanity.com/paper/2511.00053/) (2025)
- [Multimodal Meta-Learning for Time Series Regression](https://mlsanity.com/paper/2108.02842/) (2021)
- [Few-Shot Forecasting of Time-Series with Heterogeneous Channels](https://mlsanity.com/paper/2204.03456/) (2022)
- [A Survey of Few-Shot Learning for Biomedical Time Series](https://mlsanity.com/paper/2405.02485/) (2024)
- [Federated Learning with MMD-based Early Stopping for Adaptive GNSS Interference Classification](https://mlsanity.com/paper/2410.15681/) (2024)
- [Few-shot Learning for Topic Modeling](https://mlsanity.com/paper/2104.09011/) (2021)
- [Evaluation of (Un-)Supervised Machine Learning Methods for GNSS Interference Classification with Real-World Data Discrepancies](https://mlsanity.com/paper/2503.23775/) (2025)
- [Large Language Models are Few-shot Multivariate Time Series Classifiers](https://mlsanity.com/paper/2502.00059/) (2025)
- [Large Language models for Time Series Analysis: Techniques, Applications, and Challenges](https://mlsanity.com/paper/2506.11040/) (2025)
- [Spectral Propagation Graph Network for Few-shot Time Series Classification](https://mlsanity.com/paper/2202.04769/) (2022)
- [Benchmarking for Practice: Few-Shot Time-Series Crop-Type Classification on the EuroCropsML Dataset](https://mlsanity.com/paper/2504.11022/) (2025)
- [Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection](https://mlsanity.com/paper/2103.00684/) (2021)
- [TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering](https://mlsanity.com/paper/2309.04732/) (2023)
- [A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction](https://mlsanity.com/paper/2309.04733/) (2023)
- [Successive Model-Agnostic Meta-Learning for Few-Shot Fault Time Series Prognosis](https://mlsanity.com/paper/2311.02300/) (2023)
- [Adapting to the Unknown: Robust Meta-Learning for Zero-Shot Financial Time Series Forecasting](https://mlsanity.com/paper/2504.09664/) (2025)
- [Meta-learning to Address Data Shift in Time Series Classification](https://mlsanity.com/paper/2601.09018/) (2026)
- [DirPA: Addressing Prior Shift in Imbalanced Few-shot Crop-type Classification](https://mlsanity.com/paper/2603.12905/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is difficult, and where DNNs would be prone to overfitting. We leverage recent advancements in gradient-based meta-learning, and propose an approach to train a residual neural network with convolutional layers as a meta-learning agent for few-shot TSC. The network is trained on a diverse set of few-shot tasks sampled from various domains (e.g. healthcare, activity recognition, etc.) such that it can solve a target task from another domain using only a small number of training samples from the target task. Most existing meta-learning approaches are limited in practice as they assume a fixed number of target classes across tasks. We overcome this limitation in order to train a common agent across domains with each domain having different number of target classes, we utilize a triplet-loss based learning procedure that does not require any constraints to be enforced on the number of classes for the few-shot TSC tasks. To the best of our knowledge, we are the first to use meta-learning based pre-training for TSC. Our approach sets a new benchmark for few-shot TSC, outperforming several strong baselines on few-shot tasks sampled from 41 datasets in UCR TSC Archive. We observe that pre-training under the meta-learning paradigm allows the network to quickly adapt to new unseen tasks with small number of labeled instances.