arXiv:2605.17730cs.LGcs.AI2026-05

提出L-Drive框架,用隐状态上下文提升时序预测对系统突变的响应速度

L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting

论文配图:L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
图 1 · 摘自论文原文
  • 引入隐状态上下文捕捉动态变化,通过门控机制及时调整预测
  • 在多个数据集上实现更优的准确率与效率平衡,尤其在突变窗口表现更稳定
  • 适合需要快速适应环境变化的工业时序预测场景

主流多变量时间序列预测方法普遍采用直接映射范式,在观测空间中学习历史到未来的统一映射以捕捉值级依赖。然而真实系统常经历分布漂移和模式切换,此时统一映射在转折点附近会出现响应延迟,导致切换窗口内误差累积,降低预测可靠性。为此,我们提出L-Drive,一种感知变化的预测框架。L-Drive引入隐状态上下文(Latent-Context),显式刻画随时间演化的高层动态,并通过门控机制调节增量表示,提供更及时的变化线索,提升对变化区段的适应能力。此外,它采用共享块的相对位置基函数,强化段内结构建模,减少由绝对位置记忆引起的过拟合。大量实验验证了L-Drive的有效性,展现出在预测精度与计算效率之间的更优权衡。

原文摘要 · Abstract (English)

Mainstream methods for multivariate time-series forecasting largely follow the Direct-Mapping paradigm. They learn a unified mapping from history to the future in the observation space to fit value-level dependencies. However, real-world systems often undergo distribution shifts and regime changes. In such cases, a unified mapping can exhibit response lag around turning points, causing error accumulation within the switching window and reducing forecasting reliability. To address this issue, we propose L-Drive, a change-aware forecasting framework. L-Drive introduces a Latent-Context, to explicitly characterize high-level dynamics evolving over time, and uses gating to modulate increment representations. This provides more timely change cues and improves adaptation to changing segments. In addition, it incorporates patch-shared relative positional basis functions to strengthen intra-segment structural modeling and reduce overfitting caused by absolute-position memorization. Extensive experiments validate the effectiveness of L-Drive and show a better overall trade-off between forecasting accuracy and computational efficiency.

时序预测隐状态建模动态适应

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。