AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs

• URL: http://arxiv.org/abs/2601.12893v1
• Date: Mon, 19 Jan 2026 09:46:54 GMT
• Title: AdaNODEs: Test Time Adaptation for Time Series Forecasting Using Neural ODEs
• Authors: Ting Dang, Soumyajit Chatterjee, Hong Jia, Yu Wu, Flora Salim, Fahim Kawsar,
• Abstract summary: Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions.<n>This paper presents AdaNODEs, an innovative source-free TTA method tailored explicitly for time series forecasting.
• Score: 20.237470399970448
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Test time adaptation (TTA) has emerged as a promising solution to adapt pre-trained models to new, unseen data distributions using unlabeled target domain data. However, most TTA methods are designed for independent data, often overlooking the time series data and rarely addressing forecasting tasks. This paper presents AdaNODEs, an innovative source-free TTA method tailored explicitly for time series forecasting. By leveraging Neural Ordinary Differential Equations (NODEs), we propose a novel adaptation framework that accommodates the unique characteristics of distribution shifts in time series data. Moreover, we innovatively propose a new loss function to tackle TTA for forecasting tasks. AdaNODEs only requires updating limited model parameters, showing effectiveness in capturing temporal dependencies while avoiding significant memory usage. Extensive experiments with one- and high-dimensional data demonstrate that AdaNODEs offer relative improvements of 5.88\% and 28.4\% over the SOTA baselines, especially demonstrating robustness across higher severity distribution shifts.

Related papers

• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• Learning Data-Driven Uncertainty Set Partitions for Robust and Adaptive Energy Forecasting with Missing Data [0.0]
  Short-term wind power forecasting models assume the availability of input data (features) when they are deployed and in use.<n>Equipment failures, disruptions, cyberattacks may lead to missing features when such models are used operationally.<n>We use adaptive robust optimization and adversarial machine learning to develop forecasting models that seamlessly handle missing data operationally.
  arXiv  Detail & Related papers  (2025-03-26T10:38:56Z)
• 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)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [65.21599711087538]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample.<n>Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications.<n>We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning [73.75282761503581]
  We propose DiffTPT, which leverages pre-trained diffusion models to generate diverse and informative new data. Our experiments on test datasets with distribution shifts and unseen categories demonstrate that DiffTPT improves the zero-shot accuracy by an average of 5.13%.
  arXiv  Detail & Related papers  (2023-08-11T09:36:31Z)
• Towards Flexible Time-to-event Modeling: Optimizing Neural Networks via Rank Regression [17.684526928033065]
  We introduce the Deep AFT Rank-regression model for Time-to-event prediction (DART) This model uses an objective function based on Gehan's rank statistic, which is efficient and reliable for representation learning. The proposed method is a semiparametric approach to AFT modeling that does not impose any distributional assumptions on the survival time distribution.
  arXiv  Detail & Related papers  (2023-07-16T13:58:28Z)
• Out-of-distribution Few-shot Learning For Edge Devices without Model Fine-tuning [10.422316867474681]
  Few-shot learning is a promising technique to achieve personalized user experiences on edge devices. This paper proposes a plug-and-play module called Task-aware Normalization (TANO) that enables efficient and task-aware adaptation of a deep neural network without backpropagation. TANO provides stable but task-specific estimations of the normalization statistics to close the distribution gaps and achieve efficient model adaptation.
  arXiv  Detail & Related papers  (2023-04-13T07:33:22Z)
• TeST: Test-time Self-Training under Distribution Shift [99.68465267994783]
  Test-Time Self-Training (TeST) is a technique that takes as input a model trained on some source data and a novel data distribution at test time. We find that models adapted using TeST significantly improve over baseline test-time adaptation algorithms.
  arXiv  Detail & Related papers  (2022-09-23T07:47:33Z)
• Robust Continual Test-time Adaptation: Instance-aware BN and Prediction-balanced Memory [58.72445309519892]
  We present a new test-time adaptation scheme that is robust against non-i.i.d. test data streams. Our novelty is mainly two-fold: (a) Instance-Aware Batch Normalization (IABN) that corrects normalization for out-of-distribution samples, and (b) Prediction-balanced Reservoir Sampling (PBRS) that simulates i.i.d. data stream from non-i.i.d. stream in a class-balanced manner.
  arXiv  Detail & Related papers  (2022-08-10T03:05:46Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)

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.