arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09130cs.LGcs.AI
收藏

使用不变学习实现面向分布外泛化的时间序列预测

Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning

School of Computational Science and Engineering, Georgia Institute of Technology(佐治亚理工学院计算科学与工程学院)

Haoxin Liu, Harshavardhan Kamarthi, Lingkai Kong, Zhiyuan Zhao, Chao Zhang, B. Aditya Prakash

AI总结:

针对时间序列预测中的分布外泛化难题,本文提出模型无关框架 FOIL,通过代理损失、环境推断和不变表示学习提升多种 TSF 模型,最高增益达 85%。

摘要:

时间序列预测(TSF)在真实场景中具有广泛应用。由于时间序列数据具有动态特性,使 TSF 模型具备分布外(OOD)泛化能力至关重要,因为历史训练数据与未来测试数据可能具有不同的分布。本文旨在通过不变学习缓解 TSF 中固有的 OOD 问题。我们指出了面向 TSF 的不变学习所面临的根本挑战。首先,由于 TSF 中存在未观测到的核心变量,TSF 中的目标变量可能无法由输入充分确定,这破坏了不变学习的传统假设。其次,时间序列数据集缺乏足够的环境标签,而现有的环境推断方法并不适用于 TSF。为应对这些挑战,我们提出了 FOIL,这是一个与模型无关的框架,能够通过不变学习实现面向分布外泛化的时间序列预测。FOIL 采用一种新颖的代理损失来减轻未观测变量的影响。此外,FOIL 通过以下方式实施联合优化:利用多头网络在保持时间邻接结构的同时有效地交替推断环境,并在推断出的环境之间学习用于 OOD 泛化 TSF 的不变表示。我们证明,所提出的 FOIL 显著提升了多种 TSF 模型的性能,增益最高可达 85%。

英文摘要:

Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and future test data can have different distributions. In this paper, we aim to alleviate the inherent OOD problem in TSF via invariant learning. We identify fundamental challenges of invariant learning for TSF. First, the target variables in TSF may not be sufficiently determined by the input due to unobserved core variables in TSF, breaking the conventional assumption of invariant learning. Second, time-series datasets lack adequate environment labels, while existing environmental inference methods are not suitable for TSF. To address these challenges, we propose FOIL, a model-agnostic framework that enables timeseries Forecasting for Out-of-distribution generalization via Invariant Learning. FOIL employs a novel surrogate loss to mitigate the impact of unobserved variables. Further, FOIL implements a joint optimization by alternately inferring environments effectively with a multi-head network while preserving the temporal adjacency structure, and learning invariant representations across inferred environments for OOD generalized TSF. We demonstrate that the proposed FOIL significantly improves the performance of various TSF models, achieving gains of up to 85%.

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。

↑