arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09573cs.LGcs.CL
收藏

蝴蝶引发的变化:基于群组储备池Transformer的远见预测

Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer

Md Kowsher, Abdul Rafae Khan, Jia Xu

AI总结:

本文提出群组储备池Transformer,通过储备池高效处理长历史序列并降低对初始条件的敏感性,在多变量时间序列预测中显著优于现有模型,误差最高降低59%。

摘要:

在混沌系统中,两个初始条件之间的微小差异会随时间呈指数级放大,导致相距甚远的结果,这被称为蝴蝶效应。因此,遥远的未来充满不确定性,难以预测。我们提出群组储备池Transformer(Group Reservoir Transformer),通过克服混沌中的两个挑战来更准确、更稳健地预测长期事件:(1)广泛的历史序列;(2)对初始条件的敏感性。将一个储备池附加到Transformer上,以高效处理任意长的历史长度,并扩展一组储备池以降低对初始化变化的敏感性。我们的架构在多变量时间序列中持续优于最先进模型,包括TimeLLM、GPT2TS、PatchTST、DLinear、TimeNet和基线Transformer,在ETTh、ETTm和空气质量等多个领域的误差降低最高达-59%,表明蝴蝶学习的集成可以提高事件预测的充分性和确定性,尽管前往未知未来的旅程需要时间。

英文摘要:

In Chaos, a minor divergence between two initial conditions exhibits exponential amplification over time, leading to far-away outcomes, known as the butterfly effect. Thus, the distant future is full of uncertainty and hard to forecast. We introduce Group Reservoir Transformer to predict long-term events more accurately and robustly by overcoming two challenges in Chaos: (1) the extensive historical sequences and (2) the sensitivity to initial conditions. A reservoir is attached to a Transformer to efficiently handle arbitrarily long historical lengths, with an extension of a group of reservoirs to reduce the sensitivity to the initialization variations. Our architecture consistently outperforms state-of-the-art models in multivariate time series, including TimeLLM, GPT2TS, PatchTST, DLinear, TimeNet, and the baseline Transformer, with an error reduction of up to -59\% in various fields such as ETTh, ETTm, and air quality, demonstrating that an ensemble of butterfly learning can improve the adequacy and certainty of event prediction, despite of the traveling time to the unknown future.

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。

↑