Label-efficient Time Series Representation Learning: A Review
arXiv:2302.06433 · doi:10.1109/TAI.2024.3430236
Abstract
Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semi-supervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross-domain, based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field.
Accepted in the IEEE Transactions on Artificial Intelligence (TAI) https://ieeexplore.ieee.org/document/10601520
References in corpus (15)
- Deep learning for time series classification: a review
- InceptionTime: Finding AlexNet for Time Series Classification
- DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
- An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
- Time Series Data Augmentation for Deep Learning: A Survey
- Self-supervised ECG Representation Learning for Emotion Recognition
- Multi-task Self-Supervised Learning for Human Activity Detection
- Transfer learning for time series classification
- Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
- Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
- Self-supervised Autoregressive Domain Adaptation for Time Series Data
- ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data
- PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
- Contrastive Domain Adaptation for Time-Series via Temporal Mixup
- Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift