通过相关性感知适配器，提升多变量时间序列预测精度
CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter
- 将相关性矩阵分解为时变与不变两部分，用可学习多项式捕捉动态关联
- 设计双对比学习机制，精准识别部分通道间的正负相关性
- 轻量级插件式结构，仅需微调即可显著提升主流时间序列模型性能
现有时间序列基础模型多采用独立通道建模，聚焦于时序依赖的捕捉与泛化，却忽略了通道间的相关性或其不同表现形式。然而，这些相关性在多变量时间序列预测中至关重要。为此，我们提出一种轻量级、即插即用的相关性感知适配器（CoRA），仅需对时间序列基础模型进行微调，即可有效捕获多种相关性类型，从而提升预测性能。具体而言，为降低复杂度，创新性地将相关性矩阵分解为低秩时变与时不变成分；针对时变部分，引入可学习多项式以捕捉趋势或周期模式；为学习仅存在于部分通道间的正负相关性，设计新颖的双对比学习方法，通过投影层结合异质-部分对比损失进行训练，推理阶段不增加额外开销。在10个真实世界数据集上的大量实验表明，CoRA能显著提升时间序列基础模型在多变量预测中的表现。
原文摘要 · Abstract (English)
Most existing Time Series Foundation Models (TSFMs) use channel independent modeling and focus on capturing and generalizing temporal dependencies, while neglecting the correlations among channels or overlooking the different aspects of correlations. However, these correlations play a vital role in Multivariate time series forecasting. To address this, we propose a CoRrelation-aware Adapter (CoRA), a lightweight plug-and-play method that requires only fine-tuning with TSFMs and is able to capture different types of correlations, so as to improve forecast performance. Specifically, to reduce complexity, we innovatively decompose the correlation matrix into low-rank Time-Varying and Time-Invariant components. For the Time-Varying component, we further design learnable polynomials to learn dynamic correlations by capturing trends or periodic patterns. To learn positive and negative correlations that appear only among some channels, we introduce a novel dual contrastive learning method that identifies correlations through projection layers, regulated by a Heterogeneous-Partial contrastive loss during training, without introducing additional complexity in the inference stage. Extensive experiments on 10 real-world datasets demonstrate that CoRA can improve TSFMs in multivariate forecasting performance.
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。