文本真的有用吗？揭示并解决多模态时间序列预测中的文本坍缩问题
Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting
AI总结：
针对多模态时间序列预测中文本分支被忽视导致“文本坍缩”的问题，提出REST-TS方法，通过让文本分支专门预测数值主干无法解释的残差，强制其提取真实内容，实现最先进性能。
摘要：
多模态时间序列预测将数值序列与领域相关的文本报告配对，有望将世界知识注入预测流程。然而，我们揭示了现有框架中的一个关键失败模式，称为文本坍缩：文本分支收敛到与内容无关的变换，无论输入描述如何，都贡献可忽略的判别信号。我们认为文本坍缩是时间序列预测中基本不对称性的结果：数值输入与输出强自相关，使得数值主干天生占主导地位，而文本分支尽管携带互补且通常关键的信息，却未被充分利用，导致其系统性欠利用。为解决此问题，我们提出REST-TS（时间序列中文本的残差独占监督），将不对称性转化为设计原则：数值主干产生其独立的数值预测，而文本分支被独占监督以预测残差的结构化组成部分，即数值无法解释的预测差距。由于没有数值路径可以减少这些损失，文本分支必须从输入描述中提取真实内容。在多样化的现实领域和主干架构上的评估表明，REST-TS实现了最先进的性能，并一致地显示出比现有框架更高的文本分支利用率，提供了强有力的经验证据，表明对文本分支进行残差监督迫使其从输入中提取真实内容。
英文摘要：
Multimodal time series forecasting, which pairs numerical sequences with domain-relevant textual reports, promises to inject world knowledge into forecasting pipelines. However, we uncover a critical failure mode in existing frameworks that we term text collapse: the text branch converges to a content-independent transformation, contributing negligible discriminative signal regardless of the input description. We argue that text collapse is a consequence of a fundamental asymmetry in time series forecasting: the numerical input is strongly autocorrelated with the output, making the numerical backbone inherently dominant, while the text branch, despite carrying complementary and often critical information, is insufficiently utilized, leading to its systematic underexploitation. To address this, we propose \textbf{REST-TS} (\textbf{R}esidual-\textbf{E}xclusive \textbf{S}upervision for \textbf{T}ext in \textbf{T}ime \textbf{S}eries), which turns the asymmetry into a design principle: the numerical backbone produces its own independent numerical forecast, and the text branch is exclusively supervised to predict the structured components of the residual, the prediction gap that numbers cannot explain. Because no numerical pathway can reduce these losses, the text branch must extract genuine content from the input description. Evaluated across diverse real-world domains and backbone architectures, REST-TS achieves state-of-the-art performance and consistently demonstrates greater text-branch utilization than existing frameworks, providing strong empirical evidence that supervising the text branch on the residual compels it to extract genuine content from the input.
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。
