DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting
Abstract
Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth. Recent works on test-time adaptation for TSF address this by introducing lightweight calibration modules around frozen forecasters, updated using observations that become incrementally available at test time. Existing approaches typically employ channel-wise adapters, implicitly assuming that forecast residuals are inherently channel-specific. However, we observe that forecast residuals often exhibit substantial shared structure across channels, suggesting that fully independent channel-wise parameterization may be redundant. Motivated by this observation, we propose the Dual-Branch Calibration Module (DBCM), which shares adaptation capacity across channels through a shared adapter while retaining limited channel-specific flexibility through a low-rank channel-wise adapter, further enhanced by channel mixing and nonlinear gated modulation. Extensive experiments show that DBCM consistently outperforms prior methods across diverse datasets, horizons, and backbones.
Related
- RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting
- Adaptive Decomposition and Dual-Branch Linear Forecasting for Stock Price Prediction
- Constrained Genetic-Algorithm-Based PID Gain Optimization for Servo Control of a Diverter Valve in a 200 kg Gravimetric Liquid Flow Calibration Module
- Attribution-State Conformal Forecasting: Residual-Independent Explanation States for Uncertainty Calibration Under Distribution Shift
- Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization
BibTeX
@misc{jeon2026dbcm,
title = {{DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting}},
author = {Jaebyeong Jeon and Kunwoo Kang and Sang Yup Lee and Kibok Lee},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32071},
eprint = {2610.32071},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32071},
}
RIS
TY - UNPB
TI - DBCM: Dual-Branch Calibration Module for Test-Time Adaptation in Time Series Forecasting
AU - Jaebyeong Jeon
AU - Kunwoo Kang
AU - Sang Yup Lee
AU - Kibok Lee
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32071
UR - https://arxiv.org/abs/2610.32071
AB - Non-stationarity induces test-time distribution shifts in time series forecasting (TSF), resulting in forecast residuals between predictions and the corresponding ground truth. Recent works on test-time adaptation for TSF address this by introducing lightweight calibration modules around frozen forecasters, updated using observations that become incrementally available at test time. Existing approaches typically employ channel-wise adapters, implicitly assuming that forecast residuals are inherently channel-specific. However, we observe that forecast residuals often exhibit substantial shared structure across channels, suggesting that fully independent channel-wise parameterization may be redundant. Motivated by this observation, we propose the Dual-Branch Calibration Module (DBCM), which shares adaptation capacity across channels through a shared adapter while retaining limited channel-specific flexibility through a low-rank channel-wise adapter, further enhanced by channel mixing and nonlinear gated modulation. Extensive experiments show that DBCM consistently outperforms prior methods across diverse datasets, horizons, and backbones.
ER -