mlsanityData to 7 Oct 2026

CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables

arXiv 2403.01673 ↗First posted 4 Mar 2024stat.ML cs.AI cs.LGcited by 25

Not on the map. Why?

Abstract (arXiv)

For Multivariate Time Series Forecasting (MTSF), recent deep learning applications show that univariate models frequently outperform multivariate ones. To address the difficiency in multivariate models, we introduce a method to Construct Auxiliary Time Series (CATS) that functions like a 2D temporal-contextual attention mechanism, which generates Auxiliary Time Series (ATS) from Original Time Series (OTS) to effectively represent and incorporate inter-series relationships for forecasting. Key principles of ATS - continuity, sparsity, and variability - are identified and implemented through different modules. Even with a basic 2-layer MLP as core predictor, CATS achieves state-of-the-art, significantly reducing complexity and parameters compared to previous multivariate models, marking it an efficient and transferable MTSF solution.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

18 of 31 references.

References · 18

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  5. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  7. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  9. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  10. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  11. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  12. 2022Transformers in Time Series: A Surveycited by 489
6 more
  1. 2017Residual Attention Network for Image Classificationcited by 385
  2. 2017A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Predictioncited by 245
  3. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  4. 2017Conditional Time Series Forecasting with Convolutional Neural Networkscited by 121
  5. 2021Manifold-constrained Gaussian process inference for time-varying parameters in dynamic systemscited by 8
  6. 2023ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learningcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 9; 2026: 6.

25 papers.

Sort:

By area:

  1. 2024Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classificationcited by 53
  2. 2024Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformerscited by 35
  3. 2024Unlocking the Power of LSTM for Long Term Time Series Forecastingcited by 29
  4. 2024ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Imagescited by 19
  5. 2025Out-of-Distribution Generalization in Time Series: A Surveycited by 15
  6. 2024UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecastingcited by 13
  7. 2025Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecastingcited by 8
  8. 2025Selective Learning for Deep Time Series Forecastingcited by 8
  9. 2025Longitudinal Flow Matching for Trajectory Modelingcited by 6
  10. 2026Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Seriescited by 5
  11. 2024WAVE: Weighted Autoregressive Varying Gate for Time Series Forecastingcited by 3
  12. 2025SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Seriescited by 3
13 more
  1. 2024Enhanced Credit Score Prediction Using Ensemble Deep Learning Modelcited by 2
  2. 2025Cardioformer: Advancing AI in ECG Analysis with Multi-Granularity Patching and ResNetcited by 1
  3. 2025EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecastingcited by 1
  4. 2026CAPS: Unifying Attention, Recurrence, and Alignment in Transformer-based Time Series Forecastingcited by 1
  5. 2026DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecastingcited by 1
  6. 2024RW-NSGCN: A Robust Approach to Structural Attacks via Negative Samplingcited by 0
  7. 2024Pre-trained Graphformer-based Ranking at Web-scale Search (Extended Abstract)cited by 0
  8. 2024Generative Pre-trained Ranking Model with Over-parameterization at Web-Scale (Extended Abstract)cited by 0
  9. 2025Channel-Imposed Fusion: A Simple yet Effective Method for Medical Time Series Classificationcited by 0
  10. 2025Transformer Modeling for Both Scalability and Performance in Multivariate Time Seriescited by 0
  11. 2026Beyond Similarity: Temporal Operator Attention for Time Series Analysiscited by 0
  12. 2026CAST: Causal Anchored Simplex Transport for Distribution-Valued Time Seriescited by 0
  13. 2026Exogenous Dropout: A Simple, Strong Baseline for Corruption-Robust Time Series Forecasting with Covariatescited by 0