Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval

2026-02-11

AI Summary

This work addresses the limitation of existing time series models, which struggle to capture global periodic patterns extending far beyond their finite context windows. To overcome this, we propose the Global Temporal Retriever (GTR)—a lightweight, plug-and-play module that adaptively retrieves and integrates relevant periodic information from historical data through adaptive global temporal embeddings and a dynamic retrieval alignment mechanism. GTR jointly models local dependencies and long-range periodicity without requiring modifications to the backbone architecture. By incorporating two-dimensional convolutions and a residual fusion strategy, GTR achieves substantial improvements in both short- and long-term forecasting accuracy across six real-world multivariate datasets, while introducing minimal additional parameters and computational overhead.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Multivariate time series forecasting (MTSF) plays a vital role in numerous real-world applications, yet existing models remain constrained by their reliance on a limited historical context. This limitation prevents them from effectively capturing global periodic patterns that often span cycles significantly longer than the input horizon - despite such patterns carrying strong predictive signals. Naive solutions, such as extending the historical window, lead to severe drawbacks, including overfitting, prohibitive computational costs, and redundant information processing. To address these challenges, we introduce the Global Temporal Retriever (GTR), a lightweight and plug-and-play module designed to extend any forecasting model's temporal awareness beyond the immediate historical context. GTR maintains an adaptive global temporal embedding of the entire cycle and dynamically retrieves and aligns relevant global segments with the input sequence. By jointly modeling local and global dependencies through a 2D convolution and residual fusion, GTR effectively bridges short-term observations with long-term periodicity without altering the host model architecture. Extensive experiments on six real-world datasets demonstrate that GTR consistently delivers state-of-the-art performance across both short-term and long-term forecasting scenarios, while incurring minimal parameter and computational overhead. These results highlight GTR as an efficient and general solution for enhancing global periodicity modeling in MTSF tasks. Code is available at this repository: https://github.com/macovaseas/GTR.

Problem

• multivariate time series forecasting
• global periodicity
• historical context limitation
• long-term dependencies

Innovation

• Global Temporal Retrieval
• Multivariate Time Series Forecasting
• Periodicity Modeling
• Plug-and-Play Module
• Long-term Dependency