将多模态上下文信息融入时间序列预测，显著提升模型性能。
Context Matters: Leveraging Contextual Features for Time Series Forecasting
- 设计可插拔的ContextFormer，融合文本、类别、连续等多模态上下文特征。
- 在能源、交通、环境、金融等6个真实数据集上，性能比现有最优模型提升最高30%。
- 特别适合需结合外部信息（如新闻、政策）的金融与经济预测场景。
时间序列预测常受外部上下文特征影响，例如金融领域中股价预测需结合新闻文章、推文等公众情绪和政策变化。尽管这一现象普遍存在，当前最先进的预测模型因上下文异构性和多模态特性，难以有效利用此类信息。为此，我们提出ContextFormer，一种可即插即用的新方法，能精准提取丰富多模态上下文（包括分类、连续、时变及文本信息）中的预测相关特征，并无缝集成至预训练的基线预测模型中。实验表明，ContextFormer在涵盖能源、交通、环境和金融领域的多个真实数据集上，相比现有最先进模型，性能最高提升30%。
原文摘要 · Abstract (English)
Time series forecasts are often influenced by exogenous contextual features in addition to their corresponding history. For example, in financial settings, it is hard to accurately predict a stock price without considering public sentiments and policy decisions in the form of news articles, tweets, etc. Though this is common knowledge, the current state-of-the-art (SOTA) forecasting models fail to incorporate such contextual information, owing to its heterogeneity and multimodal nature. To address this, we introduce ContextFormer, a novel plug-and-play method to surgically integrate multimodal contextual information into existing pre-trained forecasting models. ContextFormer effectively distills forecast-specific information from rich multimodal contexts, including categorical, continuous, time-varying, and even textual information, to significantly enhance the performance of existing base forecasters. ContextFormer outperforms SOTA forecasting models by up to 30% on a range of real-world datasets spanning energy, traffic, environmental, and financial domains.
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。