CARNet Cycle-Conditioned Core Aggregation and Redistribution for Multivariate Time Series Forecasting

2026-07-23

AI Summary

This work addresses the challenge of efficiently modeling cross-variable dependencies under strong periodicity in multivariate time series forecasting, a limitation of existing methods. To this end, the authors propose CARNet, a novel framework that, for the first time, integrates global periodic conditioning information into an attention-free core aggregation architecture. CARNet explicitly captures periodic cross-variable dependencies through a multi-head core aggregation mechanism, achieving highly effective modeling while maintaining linear computational complexity. Extensive experiments demonstrate that CARNet consistently and significantly outperforms state-of-the-art Transformer-based and non-attention baselines across multiple real-world benchmarks and diverse prediction horizons.

Abstract

Accurately modeling cross-variate dependencies remains a key challenge in multivariate time series forecasting, particularly in the presence of strong periodic patterns. Many existing approaches rely on attention-based mechanisms that incur quadratic complexity and scale poorly with increasing numbers of variates. Recent attention-free aggregation models address this issue through linear-complexity core-based interactions, but they do not explicitly leverage the global periodic structure present in the data. To overcome this limitation, we propose CARNet, a Cycle-Conditioned Core Aggregation and Redistribution framework that integrates global recurrent cycle information into efficient core based interaction modeling via Multihead Core Aggregation. Extensive experiments on multiple real-world multivariate forecasting benchmarks demonstrate that CARNet consistently outperforms strong transformer and non-attention baselines across diverse prediction horizons while preserving linear-complexity modeling of cross-variate dependencies.

Problem

• multivariate time series forecasting
• cross-variate dependencies
• periodic patterns
• linear complexity
• attention-free modeling

Innovation

• Cycle-Conditioned
• Core Aggregation
• Linear Complexity
• Multivariate Time Series Forecasting
• Cross-variate Dependencies