UniCA: Adapting Time Series Foundation Model to General Covariate-Aware Forecasting

• URL: http://arxiv.org/abs/2506.22039v1
• Date: Fri, 27 Jun 2025 09:35:51 GMT
• Title: UniCA: Adapting Time Series Foundation Model to General Covariate-Aware Forecasting
• Authors: Lu Han, Yu Liu, Qiwen Deng, Jian Jiang, Yinbo Sun, Zhe Yu, Binfeng Wang, Xingyu Lu, Lintao Ma, Han-Jia Ye, De-Chuan Zhan,
• Abstract summary: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining.<n>Their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks.<n>We propose UniCA, a framework to bridge TSFMs with general covariate-aware forecasting.
• Score: 53.39450166672876
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their ability to handle general forecasting tasks involving diverse and often heterogeneous covariates--such as categorical variables and multimodal data (e.g., images, text)--which are typically task-specific and difficult to leverage during pretraining. To address this gap, we propose Unified Covariate Adaptation (UniCA), a framework to bridge TSFMs with general covariate-aware forecasting. UniCA first performs covariate homogenization to transform heterogeneous covariates into high-level homogeneous series representations and then fuses them via a unified attention-based fusion mechanism. UniCA is compatible and universal for adaptation with both homogeneous and heterogeneous covariates, incorporating extra covariate information while preserving the generalization ability of TSFMs.Extensive experiments on multiple unimodal and multimodal covariate-aware forecasting benchmarks demonstrate the superiority of UniCA, highlighting the promise of covariate-aware TSFM adaptation in real-world forecasting scenarios. Codes are released on https://github.com/hanlu-nju/UniCA.

Related papers

• DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Models [15.63564280210946]
  We propose DualWeaver, a framework that adapts uni-TSFMs (Uni-TSFMs) for multivariate forecasting by using a pair of learnable, structurally symmetric surrogate series.<n>Experiments on diverse real-world datasets show that DualWeaver outperforms state-of-the-art multivariate forecasters in both accuracy and stability.
  arXiv  Detail & Related papers  (2026-02-25T16:13:12Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• Adapformer: Adaptive Channel Management for Multivariate Time Series Forecasting [49.40321003932633]
  Adapformer is an advanced Transformer-based framework that merges the benefits of CI and CD methodologies through effective channel management.<n>Adapformer achieves superior performance over existing models, enhancing both predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-11-18T16:24:05Z)
• Chronos-2: From Univariate to Universal Forecasting [52.753731922908905]
  Chronos-2 is a pretrained model capable of handling univariate, multivariate, and covariate-informed forecasting tasks in a zero-shot manner.<n>It delivers state-of-the-art performance across three comprehensive benchmarks: fev-bench, GIFT-Eval, and Chronos Benchmark II.<n>The in-context learning capabilities of Chronos-2 establish it as a general-purpose forecasting model that can be used "as is" in real-world forecasting pipelines.
  arXiv  Detail & Related papers  (2025-10-17T17:00:53Z)
• CoRA: Covariate-Aware Adaptation of Time Series Foundation Models [47.20786327020571]
  Time Series Foundation Models (TSFMs) have shown significant impact through their model capacity, scalability, and zero-shot generalizations.<n>We propose a general covariate-aware adaptation (CoRA) framework for TSFMs.
  arXiv  Detail & Related papers  (2025-10-14T16:20:00Z)
• Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting [19.525630481681358]
  Conditionally Whitened Generative Models (CW-Gen) is a framework that incorporates prior information through conditional whitening.<n>CW-Gen consistently enhances predictive performance, capturing non-stationary dynamics and inter-variable correlations more effectively than prior-free approaches.
  arXiv  Detail & Related papers  (2025-09-25T09:13:37Z)
• UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data [2.6733991338938026]
  UniVarFL is a novel FL framework that emulates IID-like training dynamics directly at the client level.<n>Experiments on multiple benchmark datasets demonstrate that UniVarFL outperforms existing methods in accuracy.
  arXiv  Detail & Related papers  (2025-06-09T19:25:35Z)
• Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization [29.082583523943157]
  We propose a domain-aware adaptive normalization strategy within the Transformer architecture.<n>We replace the traditional LayerNorm with a prototype-guided dynamic normalization mechanism (ProtoNorm)<n>Our method significantly outperforms conventional pretraining techniques across both classification and forecasting tasks.
  arXiv  Detail & Related papers  (2025-04-15T06:23:00Z)
• MGCP: A Multi-Grained Correlation based Prediction Network for Multivariate Time Series [54.91026286579748]
  We propose a Multi-Grained Correlations-based Prediction Network. It simultaneously considers correlations at three levels to enhance prediction performance. It employs adversarial training with an attention mechanism-based predictor and conditional discriminator to optimize prediction results at coarse-grained level.
  arXiv  Detail & Related papers  (2024-05-30T03:32:44Z)
• ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks [9.006068771300377]
  We present ForecastGrapher, a framework for capturing the intricate temporal dynamics and inter-series correlations. Our approach is underpinned by three pivotal steps: generating custom node embeddings to reflect the temporal variations within each series; constructing an adaptive adjacency matrix to encode the inter-series correlations; and thirdly, augmenting the GNNs' expressive power by diversifying the node feature distribution.
  arXiv  Detail & Related papers  (2024-05-28T10:40:20Z)
• DGCformer: Deep Graph Clustering Transformer for Multivariate Time Series Forecasting [16.081071155397186]
  This paper proposes the Deep Graph Clustering Transformer (DGCformer) for multivariate time series forecasting. It first groups these relevant variables by a graph convolutional network integrated with an autoencoder, and a former-latter masked self-attention mechanism is then considered.
  arXiv  Detail & Related papers  (2024-05-14T09:01:33Z)
• Enhancing Multimodal Unified Representations for Cross Modal Generalization [52.16653133604068]
  We propose Training-free Optimization of Codebook (TOC) and Fine and Coarse cross-modal Information Disentangling (FCID)<n>These methods refine the unified discrete representations from pretraining and perform fine- and coarse-grained information disentanglement tailored to the specific characteristics of each modality.
  arXiv  Detail & Related papers  (2024-03-08T09:16:47Z)
• Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning [60.058083574671834]
  This paper presents a novel FCCL+, federated correlation and similarity learning with non-target distillation. For heterogeneous issue, we leverage irrelevant unlabeled public data for communication. For catastrophic forgetting in local updating stage, FCCL+ introduces Federated Non Target Distillation.
  arXiv  Detail & Related papers  (2023-09-28T09:32:27Z)
• Ensembles of Localised Models for Time Series Forecasting [7.199741890914579]
  We study how ensembling techniques can be used with generic GFMs and univariate models to solve this issue. Our work systematises and compares relevant current approaches, namely clustering series and training separate submodels per cluster. We propose a new methodology of clustered ensembles where we train multiple GFMs on different clusters of series.
  arXiv  Detail & Related papers  (2020-12-30T06:33:51Z)
• Posterior Differential Regularization with f-divergence for Improving Model Robustness [95.05725916287376]
  We focus on methods that regularize the model posterior difference between clean and noisy inputs. We generalize the posterior differential regularization to the family of $f$-divergences. Our experiments show that regularizing the posterior differential with $f$-divergence can result in well-improved model robustness.
  arXiv  Detail & Related papers  (2020-10-23T19:58:01Z)
• Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification [66.91839845347604]
  We propose an ensemble prediction model by performing diverse feature transformations after a feature extraction network. We use a batch spectral regularization term to suppress the singular values of the feature matrix during pre-training to improve the generalization ability of the model. The proposed model can then be fine tuned in the target domain to address few-shot classification.
  arXiv  Detail & Related papers  (2020-05-18T05:31:04Z)

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.