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 2601.09018cs.LGcs.AI
收藏

元学习用于解决时间序列分类中的数据漂移

Meta-learning to Address Data Shift in Time Series Classification

Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Virginia Tech(弗吉尼亚理工大学)

Samuel Myren, Nidhi Parikh, Natalie Klein

AI总结:

本文通过对比元学习与传统深度学习方法,探讨了元学习在时间序列分类中应对数据漂移的有效性,并引入SeisTask基准以促进适应学习研究。

摘要:

在工程和科学领域,传统深度学习(TDL)模型在训练数据和测试数据分布相同的情况下表现良好。然而,现实世界数据的动态性质,广泛称为数据漂移,使TDL模型容易出现性能迅速下降的问题,需要耗费成本的重新标记和低效的重新训练。元学习,使模型能够快速适应新数据,仅需少量示例,为缓解这些挑战提供了有前途的替代方案。本文系统地比较了TDL与微调和基于优化的元学习算法,以评估其在时间序列分类中处理数据漂移的能力。我们引入了一个受控、任务导向的地震基准(SeisTask),并证明元学习通常在数据稀缺的环境中实现更快、更稳定的适应,并减少过拟合现象,而在数据可用性和模型容量增加时,其优势会减弱,TDL与微调的性能相当。最后,我们研究了任务多样性对元学习的影响,发现训练和测试分布的一致性,而非多样性本身,是推动性能提升的关键。总体而言,本文提供了系统评估元学习在数据漂移下何时以及为何优于TDL的分析,并贡献SeisTask作为推动时间序列领域适应学习研究的基准。

英文摘要:

Across engineering and scientific domains, traditional deep learning (TDL) models perform well when training and test data share the same distribution. However, the dynamic nature of real-world data, broadly termed \textit{data shift}, renders TDL models prone to rapid performance degradation, requiring costly relabeling and inefficient retraining. Meta-learning, which enables models to adapt quickly to new data with few examples, offers a promising alternative for mitigating these challenges. Here, we systematically compare TDL with fine-tuning and optimization-based meta-learning algorithms to assess their ability to address data shift in time-series classification. We introduce a controlled, task-oriented seismic benchmark (SeisTask) and show that meta-learning typically achieves faster and more stable adaptation with reduced overfitting in data-scarce regimes and smaller model architectures. As data availability and model capacity increase, its advantages diminish, with TDL with fine-tuning performing comparably. Finally, we examine how task diversity influences meta-learning and find that alignment between training and test distributions, rather than diversity alone, drives performance gains. Overall, this work provides a systematic evaluation of when and why meta-learning outperforms TDL under data shift and contributes SeisTask as a benchmark for advancing adaptive learning research in time-series domains.

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。

↑