Adaptive Information Routing for Multimodal Time Series Forecasting

2025-12-10

AI Summary

To address inefficient textual information utilization in multimodal time-series forecasting, this paper proposes the Adaptive Information Routing (AIR) framework. AIR introduces a novel text-driven dynamic modulation mechanism for time-series models, leveraging an LLM-powered text refinement pipeline to extract semantically critical information, and employs gated attention routing with differentiable modality-specific weight learning to dynamically control both the fusion strategy and intensity of textual guidance on multivariate time-series features. Additionally, we establish the first standardized benchmark dedicated to multimodal time-series forecasting. Evaluated on real-world financial data—including crude oil prices and exchange rates—AIR achieves an average 18.7% reduction in MAE over strong baselines, demonstrating substantial improvements in forecasting accuracy, the effectiveness of text-guided modeling, and robust cross-domain generalization capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in practical scenarios, this is often insufficient for accurate predictions due to the limited information available. To address this challenge, multimodal time series forecasting methods which incorporate additional data modalities, mainly text data, alongside time series data have been explored. In this work, we introduce the Adaptive Information Routing (AIR) framework, a novel approach for multimodal time series forecasting. Unlike existing methods that treat text data on par with time series data as interchangeable auxiliary features for forecasting, AIR leverages text information to dynamically guide the time series model by controlling how and to what extent multivariate time series information should be combined. We also present a text-refinement pipeline that employs a large language model to convert raw text data into a form suitable for multimodal forecasting, and we introduce a benchmark that facilitates multimodal forecasting experiments based on this pipeline. Experiment results with the real world market data such as crude oil price and exchange rates demonstrate that AIR effectively modulates the behavior of the time series model using textual inputs, significantly enhancing forecasting accuracy in various time series forecasting tasks.

Problem

• Enhances forecasting by integrating text data with time series
• Dynamically guides time series models using adaptive text information
• Improves accuracy in multimodal forecasting tasks like market prediction

Innovation

• Adaptive Information Routing guides time series model dynamically
• Text-refinement pipeline uses large language model for data conversion
• AIR modulates time series model behavior with textual inputs