When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting

2026-09-10

AI Summary

研究创建了一个基准来评估文本注释对多模态时间序列预测的贡献，使用六种互信息估计器测试了合成数据，并在真实数据上验证了结果。

Abstract

Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know whether a text annotation meaningfully contributes to the forecasters prediction? This is an information-theoretic question, but to evaluate whether information-theoretic metrics can reliably measure the predictive value an annotation provides, a ground truth benchmark is needed, and none currently exist. We create a synthetic time series signal with annotations in three categories: semantically correct, incorrect, and irrelevant. Because the data generation process is fully controlled, ground-truth information content is known exactly, enabling principled evaluation of six complementary mutual information estimators (KSG, MINE, InfoNCE, CCA, PID and V-information). We show that all six estimators identify correct annotations as most informative, and are able to audit the quality of mixed text corpora, choosing the annotations that result in the best downstream forecasting results without the need for model training. Our benchmark identifies limitations of each estimator, and these are validated on seven real-world datasets, which show how estimator performance differs on weak signals. Finally, we establish practical rules for implementing these metrics for annotation auditing and fusion selection.

Problem

• multimodal forecasting
• information-theoretic metrics
• text annotations
• predictive value
• benchmark

Innovation

• information-theoretic metrics
• multimodal time-series forecasting
• synthetic benchmark
• mutual information estimators
• annotation auditing