计算机科学
判别式
人工智能
代表(政治)
分类器(UML)
任务(项目管理)
机器学习
学习迁移
特征学习
时间序列
相似性(几何)
系列(地层学)
时态数据库
编码(集合论)
原始数据
模式识别(心理学)
数据挖掘
古生物学
政治学
法学
程序设计语言
管理
集合(抽象数据类型)
经济
政治
图像(数学)
生物
作者
Emadeldeen Eldele,Mohamed Ragab,Zhenghua Chen,Min Wu,Chee Keong Kwoh,Xiaoli Li,Cuntai Guan
标识
DOI:10.24963/ijcai.2021/324
摘要
Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC), to learn time-series representation from unlabeled data. First, the raw time-series data are transformed into two different yet correlated views by using weak and strong augmentations. Second, we propose a novel temporal contrasting module to learn robust temporal representations by designing a tough cross-view prediction task. Last, to further learn discriminative representations, we propose a contextual contrasting module built upon the contexts from the temporal contrasting module. It attempts to maximize the similarity among different contexts of the same sample while minimizing similarity among contexts of different samples. Experiments have been carried out on three real-world time-series datasets. The results manifest that training a linear classifier on top of the features learned by our proposed TS-TCC performs comparably with the supervised training. Additionally, our proposed TS-TCC shows high efficiency in few-labeled data and transfer learning scenarios. The code is publicly available at https://github.com/emadeldeen24/TS-TCC.
科研通智能强力驱动
Strongly Powered by AbleSci AI