针对变量缺失的时序预测，不追求精准补全数据，而是直接服务预测任务。
Is Precise Recovery Necessary? A Task-Oriented Imputation Approach for Time Series Forecasting on Variable Subset
- 基于任务导向思想，跳过精确数据恢复，专注支持预测目标。
- 在四个数据集上平均性能优于基线方法15%。
- 适合变量不全时的时序预测场景，尤其适用于实际部署中变量缺失问题。
变量子集预测（VSF）是多变量时序预测中的特殊场景，推理阶段可用变量仅为训练阶段变量的子集。由于整个时间序列可能缺失，变量间与变量内相关性均不复存在，传统插补方法（主要聚焦于填补单个缺失点）效果受限。受特征工程启发——并非所有变量都对预测有益，我们提出面向任务的插补框架（TOI-VSF），将重点从精确数据恢复转向直接支持下游预测任务。TOI-VSF包含一个与预测模型无关的自监督插补模块，可填补缺失变量并保留时间序列的关键特征与动态模式；同时采用插补与预测联合学习策略，确保插补过程与预测目标对齐。在四个数据集上的大量实验表明，该方法平均性能优于基线方法15%。
原文摘要 · Abstract (English)
Variable Subset Forecasting (VSF) refers to a unique scenario in multivariate time series forecasting, where available variables in the inference phase are only a subset of the variables in the training phase. VSF presents significant challenges as the entire time series may be missing, and neither inter- nor intra-variable correlations persist. Such conditions impede the effectiveness of traditional imputation methods, primarily focusing on filling in individual missing data points. Inspired by the principle of feature engineering that not all variables contribute positively to forecasting, we propose Task-Oriented Imputation for VSF (TOI-VSF), a novel framework shifts the focus from accurate data recovery to directly support the downstream forecasting task. TOI-VSF incorporates a self-supervised imputation module, agnostic to the forecasting model, designed to fill in missing variables while preserving the vital characteristics and temporal patterns of time series data. Additionally, we implement a joint learning strategy for imputation and forecasting, ensuring that the imputation process is directly aligned with and beneficial to the forecasting objective. Extensive experiments across four datasets demonstrate the superiority of TOI-VSF, outperforming baseline methods by $15\%$ on average.
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。