Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TriTS: Time Series Forecasting from a Multimodal Perspective

About

Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology. However, Long-term Time Series Forecasting (LTSF) remains a significant challenge because real-world signals contain highly entangled temporal dynamics that are difficult to fully capture from a purely 1D perspective. To break this representation bottleneck, we propose TriTS, a novel cross-modal disentanglement framework that projects 1D time series into orthogonal time, frequency, and 2D-vision spaces.To seamlessly bridge the 1D-to-2D modality gap without the prohibitive $O(N^2)$ computational overhead of Vision Transformers (ViTs), we introduce a Period-Aware Reshaping strategy and incorporate Visual Mamba (Vim). This approach efficiently models cross-period dependencies as global visual textures while maintaining linear computational complexity. Complementing this, we design a Multi-Resolution Wavelet Mixing (MR-WM) module for the frequency modality, which explicitly decouples non-stationary signals into trend and noise components to achieve fine-grained time-frequency localization. Finally, a streaming linear branch is retained in the time domain to anchor numerical stability. By dynamically fusing these three complementary representations, TriTS effectively adapts to diverse data contexts. Extensive experiments across multiple benchmark datasets demonstrate that TriTS achieves state-of-the-art (SOTA) performance, fundamentally outperforming existing vision-based forecasters by drastically reducing both parameter count and inference latency.

Xiang Ao• 2026

Related benchmarks

TaskDatasetResultRank
Long-term time-series forecastingETTh1
MAE0.412
575
Long-term time-series forecastingWeather
MSE0.218
525
Long-term time-series forecastingETTm1
MSE0.331
461
Long-term time-series forecastingETTm2
MSE0.249
455
Long-term time-series forecastingTraffic
MSE0.399
427
Long-term time-series forecastingECL
MSE0.165
163
Time Series ForecastingETTh2
MAE0.372
75
Multivariate long-term forecastingETTm1 (Avg)
MSE0.379
29
Long-term forecastingETTm2 T=720
MSE0.361
29
Long-term forecastingETTm1 T=720
MSE0.447
29
Showing 10 of 20 rows

Other info

Follow for update