arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.07869cs.LG
收藏

生成时间序列的系统性评估及其在自监督预训练中的作用

A Systematic Evaluation of Generated Time Series and Their Effects in Self-Supervised Pretraining

Visa Research(维萨研究院);University of California, Riverside(加州大学河滨分校)

Audrey Der, Chin-Chia Michael Yeh, Xin Dai, Huiyuan Chen, Yan Zheng, Yujie Fan, Zhongfang Zhuang, Vivian Lai, Junpeng Wang, Liang Wang, Wei Zhang, Eamonn Keogh

AI总结:

针对自监督时间序列预训练模型表现不及简单监督模型的问题,测试六种时间序列生成方法,发现用更多生成样本替代真实预训练数据可显著提升分类性能。

摘要:

自监督预训练模型(PTMs)已在计算机视觉和自然语言处理任务中展现出卓越性能。这些成功促使研究者为时间序列数据设计PTM。在我们的实验中,大多数自监督时间序列PTM的表现都不及简单的监督模型。我们假设这一不理想现象可能由数据稀缺导致。对此,我们测试了六种时间序列生成方法,将生成数据替代真实数据用于预训练,并检验其对分类性能的影响。结果表明,用数量更多的纯生成样本替代真实数据预训练集可带来显著提升。

英文摘要:

Self-supervised Pretrained Models (PTMs) have demonstrated remarkable performance in computer vision and natural language processing tasks. These successes have prompted researchers to design PTMs for time series data. In our experiments, most self-supervised time series PTMs were surpassed by simple supervised models. We hypothesize this undesired phenomenon may be caused by data scarcity. In response, we test six time series generation methods, use the generated data in pretraining in lieu of the real data, and examine the effects on classification performance. Our results indicate that replacing a real-data pretraining set with a greater volume of only generated samples produces noticeable improvement.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑