arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2108.04443cs.LGcs.AI
收藏

AdaRNN:时间序列的自适应学习和预测

AdaRNN: Adaptive Learning and Forecasting of Time Series

Nanjing University(南京大学);Microsoft Research Asia(微软亚洲研究院);National University of Singapore(新加坡国立大学);Nanyang Technological University(南洋理工大学);Zhejiang University(浙江大学)

Yuntao Du, Jindong Wang, Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu, Chongjun Wang

摘要:

时间序列在现实世界中有着广泛的应用,并且被认为是难以预测的。由于其统计特性随时间变化,其分布也随时间变化,这将给现有方法带来严重的分布偏移问题。然而,它仍然是未探索的分布的角度来模拟的时间序列。在本文中,我们称之为时间协变量偏移(TCS)。本文提出了自适应RNN(AdaRNN)来解决TCS问题,通过建立一个自适应模型,以及对看不见的测试数据的推广。AdaRNN是由两个新的算法依次组成。首先,我们提出了时间分布表征,以更好地表征TS中的分布信息。其次,我们提出了时间分布匹配,以减少TS的分布不匹配学习自适应TS模型。AdaRNN是一个集成了灵活分布距离的通用框架。在人类活动识别、空气质量预测和金融分析方面的实验表明,AdaRNN的分类准确率为2.6%,并将RMSE显著降低了9.0%。我们还表明,时间分布匹配算法可以扩展到Transformer结构,以提高其性能。

英文摘要:

Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes temporally, which will cause severe distribution shift problem to existing methods. However, it remains unexplored to model the time series in the distribution perspective. In this paper, we term this as Temporal Covariate Shift (TCS). This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data. AdaRNN is sequentially composed of two novel algorithms. First, we propose Temporal Distribution Characterization to better characterize the distribution information in the TS. Second, we propose Temporal Distribution Matching to reduce the distribution mismatch in TS to learn the adaptive TS model. AdaRNN is a general framework with flexible distribution distances integrated. Experiments on human activity recognition, air quality prediction, and financial analysis show that AdaRNN outperforms the latest methods by a classification accuracy of 2.6% and significantly reduces the RMSE by 9.0%. We also show that the temporal distribution matching algorithm can be extended in Transformer structure to boost its performance.

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。

↑