Label-efficient Time Series Representation Learning: A Review
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSelf-Supervised LearningTime SeriesTime Series AnalysisTransfer LearningSimilar Papers 제목 키워드 기반
Unsupervised Representation Learning for Time Series: A Review
Unsupervised representation learning approaches aim to learn discriminative feature representations from unlabeled data, without the requirement of annotating every sample. Enabling unsupervised representation learning i…
Contrastive LearningRepresentation LearningTime SeriesSelf-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training a…
Anomaly DetectionSelf-Supervised LearningTime SeriesTime Series Analysis+1Time Series Data Augmentation for Deep Learning: A Survey
Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the la…
Anomaly DetectionData AugmentationDeep LearningGeneral Classification+4Automated Label Generation for Time Series Classification with Representation Learning: Reduction of Label Cost for Training
Time-series generated by end-users, edge devices, and different wearables are mostly unlabelled. We propose a method to auto-generate labels of un-labelled time-series, exploiting very few representative labelled time-se…
Representation LearningTime SeriesTime Series AnalysisTime Series ClassificationTCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
Recent works have demonstrated the superiority of supervised Convolutional Neural Networks (CNNs) in learning hierarchical representations from time series data for successful classification. These methods require suffic…
ClusteringGenerative Adversarial NetworkTime SeriesTime Series Classification