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 2203.08321cs.LG
收藏

ADATIME:面向时间序列数据领域自适应的基准测试套件

ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data

Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院);Centre for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心);Nanyang Technological University(南洋理工大学)

Mohamed Ragab, Emadeldeen Eldele, Wee Ling Tan, Chuan-Sheng Foo, Zhenghua Chen, Min Wu, Chee-Keong Kwoh, Xiaoli Li

AI总结:

针对时间序列领域自适应研究评估不统一、违背无监督假设的问题,提出AdaTime基准套件,统一评估框架并验证视觉域自适应方法经调参后在时序任务上具竞争力,为领域后续研究奠基。

摘要:

无监督领域自适应方法旨在在与训练数据分布不同(存在偏移)的无标注测试数据上取得良好的泛化效果。这类方法通常基于图像数据开发,其在时间序列数据上的应用探索相对较少。现有的时间序列领域自适应研究在评估方案、数据集和骨干神经网络架构方面存在不一致性。此外,研究中常使用有标注的目标域数据进行模型选择,这违背了无监督领域自适应的基本假设。为解决这些问题,我们开发了一套基准评估套件AdaTime,用于系统、公平地评估不同领域自适应方法在时间序列数据上的表现。具体而言,我们统一了骨干神经网络架构和基准数据集,同时探索了更贴合实际的模型选择方法,这类方法无需标注数据或仅需少量标注样本即可运行。我们的评估涵盖了将前沿的视觉领域自适应方法适配到时间序列数据的场景,也包含了近期专门针对时间序列数据开发的方法。我们开展了大量实验,在5个代表性数据集、共50个跨域场景下评估了11种前沿方法。结果表明,经过精心的超参数选择,视觉领域自适应方法的性能与专为时间序列领域自适应提出的方法相当。此外,我们发现超参数可以基于贴合实际的模型选择方法进行选取。本研究揭示了领域自适应方法应用于时间序列数据的实用洞见,为该领域的后续研究奠定了坚实基础。代码可在github.com/emadeldeen24/AdaTime获取。

英文摘要:

Unsupervised domain adaptation methods aim to generalize well on unlabeled test data that may have a different (shifted) distribution from the training data. Such methods are typically developed on image data, and their application to time series data is less explored. Existing works on time series domain adaptation suffer from inconsistencies in evaluation schemes, datasets, and backbone neural network architectures. Moreover, labeled target data are often used for model selection, which violates the fundamental assumption of unsupervised domain adaptation. To address these issues, we develop a benchmarking evaluation suite (AdaTime) to systematically and fairly evaluate different domain adaptation methods on time series data. Specifically, we standardize the backbone neural network architectures and benchmarking datasets, while also exploring more realistic model selection approaches that can work with no labeled data or just a few labeled samples. Our evaluation includes adapting state-of-the-art visual domain adaptation methods to time series data as well as the recent methods specifically developed for time series data. We conduct extensive experiments to evaluate 11 state-of-the-art methods on five representative datasets spanning 50 cross-domain scenarios. Our results suggest that with careful selection of hyper-parameters, visual domain adaptation methods are competitive with methods proposed for time series domain adaptation. In addition, we find that hyper-parameters could be selected based on realistic model selection approaches. Our work unveils practical insights for applying domain adaptation methods on time series data and builds a solid foundation for future works in the field. The code is available at \href{https://github.com/emadeldeen24/AdaTime}{github.com/emadeldeen24/AdaTime}.

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。

↑