Towards Principled Test-Time Adaptation for Time Series Forecasting

• URL: http://arxiv.org/abs/2605.17250v1
• Date: Sun, 17 May 2026 04:15:54 GMT
• Title: Towards Principled Test-Time Adaptation for Time Series Forecasting
• Abstract summary: Test-time adaptation (TTA) has emerged as a promising approach for improving time series forecasting (TSF) under distribution shift.<n>Existing TSF-TTA methods differ in how they utilize revealed targets, yet the resulting adaptation protocols remain heterogeneous.<n>We propose an adaptation protocol based solely on matured ground truth, yielding a more principled setting for adaptation.
• Score: 6.418791709373276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time adaptation (TTA) has recently emerged as a promising approach for improving time series forecasting (TSF) under distribution shift. Existing TSF-TTA methods differ in how they utilize revealed targets, yet the resulting adaptation protocols remain heterogeneous and lack a clearly unified formulation. To address this issue, we revisit TSF-TTA from the perspective of protocol cleanliness and propose an adaptation protocol based solely on matured ground truth, yielding a more principled setting for adaptation. Under this protocol, we further diagnose existing adapters in the frequency domain and find that their prediction corrections often exhibit limited and weakly structured spectral modifications. Motivated by this diagnosis, we propose Frequency-Aware Calibration (FAC), a lightweight calibration method that directly parameterizes prediction corrections in the frequency domain. Across diverse datasets, forecasting horizons, and source forecasters, FAC achieves competitive and consistent performance while requiring substantially fewer trainable parameters than the compared TSF-TTA adapters.

Related papers

• FRWKV+: Adaptive Periodic-Position Branch Interaction for Frequency-Space Linear Time Series Forecasting [9.255829167355804]
  Long-term time series forecasting is essential for decision making in energy, finance, transportation, and healthcare systems.<n>Recent lightweight forecasting models improve efficiency by operating in transformed or linearized spaces.<n>We propose FRWKV+, an enhanced FRWKV forecasting model for selective periodic-position branch interaction.
  arXiv  Detail & Related papers  (2026-05-15T07:25:13Z)
• Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining [3.9486037760311725]
  Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models.<n>Prior studies have observed that TPT often produces poorly calibrated models, raising concerns about the reliability of their predictions.<n>We introduce Flatness-aware Prompt Pretraining (FPP), a simple yet effective pretraining framework for TPT that initializes prompts within flatter regions of the loss landscape prior to adaptation.
  arXiv  Detail & Related papers  (2026-04-30T11:01:23Z)
• CANDI: Curated Test-Time Adaptation for Multivariate Time-Series Anomaly Detection Under Distribution Shift [48.29742059729268]
  Test-time adaptation (TTA) updates a pre-trained model on-the-fly using only unlabeled test data.<n>In this study, we propose CANDI, a novel TTA framework that selectively identifies and adapts to potential false positives while preserving pre-trained knowledge.
  arXiv  Detail & Related papers  (2026-04-02T10:01:11Z)
• TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting [67.91113180885601]
  TimeAPN explicitly models and predicts non-stationary factors from both the time and frequency domains.<n>TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons.<n>It outperforms state-of-the-art reversible normalization methods.
  arXiv  Detail & Related papers  (2026-03-18T07:21:24Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Rethinking Test-Time Training: Tilting The Latent Distribution For Few-Shot Source-Free Adaptation [3.5808917363708743]
  We study test-time adaptation of foundation models for few-shot classification under a completely frozen-model regime.<n>We propose arguably the first training-free inference method that adapts predictions to the new task by performing a change of measure over the latent embedding distribution induced by the encoder.
  arXiv  Detail & Related papers  (2026-02-02T18:17:29Z)
• Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation [39.7344214193566]
  We introduce a pioneering test-time adaptation framework tailored for time series forecasting (TSF)<n>TAFAS, the proposed approach to TSF-TTA, flexibly adapts source forecasters to continuously shifting test distributions while preserving the core semantic information learned during pre-training.<n>The novel utilization of partially-observed ground truth and gated calibration module enables proactive, robust, and model-agnostic adaptation of source forecasters.
  arXiv  Detail & Related papers  (2025-01-09T04:59:15Z)
• Enhancing Test Time Adaptation with Few-shot Guidance [62.49199492255226]
  Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data.<n>Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data.<n>We develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA.
  arXiv  Detail & Related papers  (2024-09-02T15:50:48Z)
• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift [28.73747033245012]
  We introduce a universal calibration methodology for the detection and adaptation of context-driven distribution shifts. A novel CDS detector, termed the "residual-based CDS detector" or "Reconditionor", quantifies the model's vulnerability to CDS. A high Reconditionor score indicates a severe susceptibility, thereby necessitating model adaptation.
  arXiv  Detail & Related papers  (2023-10-23T11:58:01Z)
• On Pitfalls of Test-Time Adaptation [82.8392232222119]
  Test-Time Adaptation (TTA) has emerged as a promising approach for tackling the robustness challenge under distribution shifts. We present TTAB, a test-time adaptation benchmark that encompasses ten state-of-the-art algorithms, a diverse array of distribution shifts, and two evaluation protocols.
  arXiv  Detail & Related papers  (2023-06-06T09:35:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.