T3Time：通过自适应多头对齐与残差融合的三模态时间序列预测
T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion
AI总结：
提出T3Time三模态框架，结合时间、频谱与提示分支，通过自适应多头对齐和残差融合，在多元时间序列预测中平均降低MSE 3.28%，MAE 2.29%，并展现少样本泛化优势。
摘要：
多元时间序列预测（MTSF）旨在对变量间的时间动态进行建模以预测未来趋势。基于Transformer的模型和大语言模型（LLMs）因其捕获长程依赖和模式的能力而显示出潜力。然而，当前方法往往依赖刚性的归纳偏置，忽略变量间交互，或采用静态融合策略，限制了跨预测视野的适应性。这些局限在捕捉时间序列数据中细微的、特定于视野的关系时造成瓶颈。为解决此问题，我们提出T3Time，一种新颖的三模态框架，包含时间、频谱和提示分支，其中专用的频率编码分支捕获周期结构，并带有门控机制，该机制基于预测视野学习时间特征与频谱特征之间的优先级。我们还提出了一种机制，通过基于特征动态加权每个头的重要性，自适应地聚合多个跨模态对齐头。在基准数据集上的大量实验表明，我们的模型持续优于最先进的基线，平均MSE降低3.28%，MAE降低2.29%。此外，它在少样本学习设置中表现出强泛化能力：使用5%的训练数据，MSE和MAE分别降低4.13%和1.91%；使用10%的数据，平均降低3.62%和1.98%。代码：https://github.com/monaf-chowdhury/T3Time/
英文摘要：
Multivariate time series forecasting (MTSF) seeks to model temporal dynamics among variables to predict future trends. Transformer-based models and large language models (LLMs) have shown promise due to their ability to capture long-range dependencies and patterns. However, current methods often rely on rigid inductive biases, ignore intervariable interactions, or apply static fusion strategies that limit adaptability across forecast horizons. These limitations create bottlenecks in capturing nuanced, horizon-specific relationships in time-series data. To solve this problem, we propose T3Time, a novel trimodal framework consisting of time, spectral, and prompt branches, where the dedicated frequency encoding branch captures the periodic structures along with a gating mechanism that learns prioritization between temporal and spectral features based on the prediction horizon. We also proposed a mechanism which adaptively aggregates multiple cross-modal alignment heads by dynamically weighting the importance of each head based on the features. Extensive experiments on benchmark datasets demonstrate that our model consistently outperforms state-of-the-art baselines, achieving an average reduction of 3.28% in MSE and 2.29% in MAE. Furthermore, it shows strong generalization in few-shot learning settings: with 5% training data, we see a reduction in MSE and MAE by 4.13% and 1.91%, respectively; and with 10% data, by 3.62% and 1.98% on average. Code - https://github.com/monaf-chowdhury/T3Time/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
