T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20597-20605
DOI: 10.1609/aaai.v40i25.39196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Abdul Monaf Chowdhury und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
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 will be released upon publication.
Zitieren
APA
Chowdhury, A. M., Akter, R., & Arib, S. H. (2026). T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20597-20605. https://doi.org/10.1609/aaai.v40i25.39196
Vancouver
Chowdhury AM, Akter R, Arib SH. T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20597-20605. doi:10.1609/aaai.v40i25.39196
BibTeX
@article{Chowdhury2026,
author = {Chowdhury, Abdul Monaf and Akter, Rabeya and Arib, Safaeid Hossain},
title = {T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {25},
pages = {20597--20605},
doi = {10.1609/aaai.v40i25.39196}
}
EUVIMED