发表机构
North South University; Apurba Technologies（南北大学; 阿普尔巴科技公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多变量时间序列预测中交叉变量依赖建模难题，提出CARNet框架，通过多头核心聚合将全局循环信息融入基于核心的交互建模，实验证明其在不同预测范围优于基线，且保持线性复杂度。
AI 中文摘要
在多变量时间序列预测中，准确建模交叉变量依赖关系仍是关键挑战，尤其是存在强周期模式时。许多现有方法依赖基于注意力的机制，具有二次复杂度且随变量数量增加扩展性差。近期无注意力聚合模型通过基于线性复杂度核心的交互解决此问题，但未明确利用数据中的全局周期结构。为克服这一限制，我们提出CARNet，一个循环条件核心聚合与重新分配框架，通过多头核心聚合将全局循环信息集成到高效的基于核心的交互建模中。在多个真实世界多变量预测基准上的广泛实验表明，CARNet在不同预测范围内始终优于强大的变压器和非注意力基线，同时保留交叉变量依赖关系的线性复杂度建模。
英文摘要
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.
CommentsAccepted at ECML PKDD 2026 (Research Track). Shortlisted for Best Research Track Student Paper Award
