Safety
Time-o1: Time-Series Forecasting Needs Transformed Label Alignment
arXiv:2505.17847v3 Announce Type: replace-cross Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared
arXiv:2505.17847v3 Announce Type: replace-cross Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared error, but this study reveals two critical limitations: (1) it ignores the presence of label autocorrelation, which biases it from the true label sequence likelihood; (2) it involves excessive number of tasks, which complicates optimization, especially for long-term forecasting. To address these issues, we introduce Time-o1, a transform-enhanced loss function for time-series forecasting. The central idea is to transform the label sequence into decorrelated components with discriminated significance. Models are then trained to align the most significant components, thereby effectively mitigating label autocorrelation and reducing task amount. Experiments demonstrate that Time-o1 achieves state-of-the-art performance and is compatible with various forecast models. Code is available at https://github.com/Master-PLC/Time-o1.
Related
- DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
- PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
- Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
Source: arXiv cs.AI | 2026-10-07