Guidelines for Augmentation Selection in Contrastive Learning for Time Series Classification
Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical component in contrastive learning, where different augmentations can dramatically impact performance, sometimes influencing accuracy by over 30%. However, the selection of augmentations is predominantly empirical which can be suboptimal, or grid searching that is time-consuming. In this paper, we establish a principled framework for selecting augmentations based on dataset characteristics such as trend and seasonality. Specifically, we construct 12 synthetic datasets incorporating trend, seasonality, and integration weights. We then evaluate the effectiveness of 8 different augmentations across these synthetic datasets, thereby inducing generalizable associations between time series characteristics and augmentation efficiency. Additionally, we evaluated the induced associations across 6 real-world datasets encompassing domains such as activity recognition, disease diagnosis, traffic monitoring, electricity usage, mechanical fault prognosis, and finance. These real-world datasets are diverse, covering a range from 1 to 12 channels, 2 to 10 classes, sequence lengths of 14 to 1280, and data frequencies from 250 Hz to daily intervals. The experimental results show that our proposed trend-seasonality-based augmentation recommendation algorithm can accurately identify the effective augmentations for a given time series dataset, achieving an average Recall@3 of 0.667, outperforming baselines. Our work provides guidance for studies employing contrastive learning in time series analysis, with wide-ranging applications. All the code, datasets, and analysis results will be released at https://github.com/DL4mHealth/TS-Contrastive-Augmentation-Recommendation.
Code (1)
Tasks
Activity RecognitionContrastive LearningPrognosisTime SeriesTime Series AnalysisTime Series ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Time Series Contrastive Learning with Information-Aware Augmentations
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key…
Contrastive LearningOpen-Ended Question AnsweringRepresentation LearningTime SeriesParametric Augmentation for Time Series Contrastive Learning
Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in…
Contrastive LearningData AugmentationRepresentation LearningTime SeriesInformation-Aware Time Series Meta-Contrastive Learning
Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key…
Contrastive LearningMeta-LearningOpen-Ended Question AnsweringRepresentation Learning+2Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting usefu…
Contrastive LearningData AugmentationLinear evaluationRepresentation Learning+6LEAVES: Learning Views for Time-Series Data in Contrastive Learning
Contrastive learning, a self-supervised learning method that can learn representations from unlabeled data, has been developed promisingly. Many methods of contrastive learning depend on data augmentation techniques, whi…
Contrastive LearningData AugmentationSelf-Supervised LearningTime Series+1