CITRAS: Covariate-Informed Transformer for Time Series Forecasting

• URL: http://arxiv.org/abs/2503.24007v3
• Date: Wed, 06 Aug 2025 11:46:11 GMT
• Title: CITRAS: Covariate-Informed Transformer for Time Series Forecasting
• Abstract summary: We propose CITRAS, a decoder-only Transformer that flexibly leverages multiple targets, past covariates, and future covariates.<n>We show that CITRAS outperforms state-of-the-art models on thirteen real-world benchmarks.
• Score: 0.49157446832511503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In practical time series forecasting, covariates provide rich contextual information that can potentially enhance the forecast of target variables. Although some covariates extend into the future forecasting horizon (e.g., calendar events, discount schedules), most multivariate models fail to leverage this pivotal insight due to the length discrepancy with target variables. Additionally, capturing the dependency between target variables and covariates is non-trivial, as models must precisely reflect the local impact of covariates while also capturing global cross-variate dependencies. To overcome these challenges, we propose CITRAS, a decoder-only Transformer that flexibly leverages multiple targets, past covariates, and future covariates. While preserving strong autoregressive capabilities, CITRAS introduces two novel mechanisms in patch-wise cross-variate attention: Key-Value (KV) Shift and Attention Score Smoothing. KV Shift seamlessly incorporates future covariates into the forecasting of target variables based on their concurrent dependencies. Additionally, Attention Score Smoothing refines locally accurate patch-wise cross-variate dependencies into global variate-level dependencies by smoothing the past series of attention scores. Experimentally, CITRAS outperforms state-of-the-art models on thirteen real-world benchmarks from both covariate-informed and multivariate settings, demonstrating its versatile ability to leverage cross-variate and cross-time dependencies for improved forecasting accuracy.

Related papers

• Multivariate Time Series Forecasting needs Cross Variable Loss [11.325603740473376]
  We propose a plug-in structural regularizer that constrains forecast residuals on a cross-variable graph.<n>CvLoss penalizes inconsistent edge-wise residual differences over forecast patches, encouraging consistency across both synchronous and asynchronous interactions.<n>Our experiments show that CvLoss consistently improves competitive forecasting models, outperforms representative learning objectives, and is compatible with a variety of forecasting backbones.
  arXiv  Detail & Related papers  (2026-08-06T08:22:45Z)
• 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)
• CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables [20.703629642499664]
  CrossLinear is a novel Linear-based forecasting model that addresses the challenges of modeling dependencies between variables.<n>This lightweight module captures the dependencies between variables with minimal computational cost and seamlessly integrates into existing neural networks.<n>Experiments on 12 real-world datasets demonstrate that CrossLinear achieves superior performance in both short-term and long-term forecasting tasks.
  arXiv  Detail & Related papers  (2025-05-29T05:34:40Z)
• Gateformer: Advancing Multivariate Time Series Forecasting through Temporal and Variate-Wise Attention with Gated Representations [2.2091590689610823]
  We re-purpose the Transformer architecture to model both cross-time and cross-variate dependencies. Our method achieves state-of-the-art performance across 13 real-world datasets, delivering performance improvements up to 20.7% over original models.
  arXiv  Detail & Related papers  (2025-05-01T04:59:05Z)
• Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models [2.6061534894032907]
  We introduce textbfConfidence-Calibrated Covariate Shift Correction (CalShift) -- a unified approach that combines a Fisher information penalty to mitigate covariate shift and a Confidence Misalignment Penalty (CMP) to reduce overconfidence in misclassified examples.<n>CalShift significantly improves model calibration, achieving up to a 5.82% reduction in Expected Error (ECE)<n>Our results highlight CalShift as a promising strategy for building robust and reliable low-shot vision-language systems for real-world applications.
  arXiv  Detail & Related papers  (2025-02-11T10:10:15Z)
• Timer-XL: Long-Context Transformers for Unified Time Series Forecasting [67.83502953961505]
  We present Timer-XL, a causal Transformer for unified time series forecasting.<n>Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-10-07T07:27:39Z)
• TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting [49.6208017412376]
  TimeBridge is a novel framework designed to bridge the gap between non-stationarity and dependency modeling. TimeBridge consistently achieves state-of-the-art performance in both short-term and long-term forecasting.
  arXiv  Detail & Related papers  (2024-10-06T10:41:03Z)
• DLFormer: Enhancing Explainability in Multivariate Time Series Forecasting using Distributed Lag Embedding [4.995397953581609]
  This study introduces DLFormer, an attention-based architecture integrated with distributed lag embedding. It showcases superior performance improvements compared to existing attention-based high-performance models.
  arXiv  Detail & Related papers  (2024-08-29T20:39:54Z)
• Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers [55.475142494272724]
  Time series prediction is crucial for understanding and forecasting complex dynamics in various domains. We introduce GridTST, a model that combines the benefits of two approaches using innovative multi-directional attentions. The model consistently delivers state-of-the-art performance across various real-world datasets.
  arXiv  Detail & Related papers  (2024-05-22T16:41:21Z)
• VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting [1.5165632546654102]
  We propose Variable Correlation Transformer (VCformer) to mine the correlations among variables. VCA calculates and integrates the cross-correlation scores corresponding to different lags between queries and keys. Inspired by Koopman dynamics theory, we also develop Koopman Temporal Detector (KTD) to better address the non-stationarity in time series.
  arXiv  Detail & Related papers  (2024-05-19T07:39:22Z)
• Evaluating the effectiveness of predicting covariates in LSTM Networks for Time Series Forecasting [0.0]
  We introduce a novel approach using seasonal time segments in combination with an RNN architecture, which is both simple and extremely effective over long forecast horizons. Our findings reveal that under certain conditions jointly training covariates with target variables can improve overall performance of the model.
  arXiv  Detail & Related papers  (2024-04-29T09:51:25Z)
• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables [75.83318701911274]
  TimeXer ingests external information to enhance the forecasting of endogenous variables. TimeXer achieves consistent state-of-the-art performance on twelve real-world forecasting benchmarks.
  arXiv  Detail & Related papers  (2024-02-29T11:54:35Z)
• TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [57.4208255711412]
  Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS) We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-02T16:45:19Z)
• Cross-LKTCN: Modern Convolution Utilizing Cross-Variable Dependency for Multivariate Time Series Forecasting Dependency for Multivariate Time Series Forecasting [9.433527676880903]
  Key to accurate forecasting results is capturing the long-term dependency between each time step. Recent methods mainly focus on the cross-time dependency but seldom consider the cross-variable dependency. We propose a modern pure convolution structure, namely Cross-LKTCN, to better utilize both cross-time and cross-variable dependency.
  arXiv  Detail & Related papers  (2023-06-04T10:50:52Z)
• Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling [46.75628526959982]
  We make the first attempt to integrate variational sequential neural learning with copula-based dependence modeling. Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across time series. It outperforms benchmarks including linear models, volatility models, deep neural networks, and variational recurrent networks in cross-market portfolio forecasting.
  arXiv  Detail & Related papers  (2023-05-09T08:19:08Z)
• Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift [50.98086766507025]
  We propose a simple-yet-effective data augmentation strategy, Adversarial Invariant Augmentation (AIA) AIA aims to extrapolate and generate new environments, while concurrently preserving the original stable features during the augmentation process.
  arXiv  Detail & Related papers  (2022-11-05T07:55:55Z)
• Multi-Target XGBoostLSS Regression [91.3755431537592]
  We present an extension of XGBoostLSS that models multiple targets and their dependencies in a probabilistic regression setting. Our approach outperforms existing GBMs with respect to runtime and compares well in terms of accuracy.
  arXiv  Detail & Related papers  (2022-10-13T08:26:14Z)
• Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
  We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
  arXiv  Detail & Related papers  (2020-06-19T05:08:43Z)
• Transformer Hawkes Process [79.16290557505211]
  We propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies. THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin. We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.
  arXiv  Detail & Related papers  (2020-02-21T13:48:13Z)

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.