mlsanityData to 7 Oct 2026

Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting

arXiv 2607.22299 ↗First posted 24 Jul 2026stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific information. We introduce Hopformer (Homogeneity-Pursuit Transformer), a two-stage framework that addresses this challenge. In the first stage, we perform a Sparsity Pattern Aggregation (SPA) scheme extracting a common low-variance trend that incorporates the covariates. This acts as a homogenization layer. In the second stage, a LoRA-fine-tuned Transformer models the remaining complex dependencies in the residual. Our method is theoretically grounded. We prove that SPA achieves a near-optimal bias-variance trade-off via an oracle inequality. We also provide generalization bounds for the second stage under dependent time series data. Hopformer sets a new state of the art, improving MASE by an average of 6.56% across synthetic and real-world forecasting benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

27 of 45 references.

References · 27

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  6. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  7. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  8. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  9. 2023A decoder-only foundation model for time-series forecastingcited by 650
  10. 2019Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecastingcited by 606
  11. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  12. 2017Information-theoretic analysis of generalization capability of learning algorithmscited by 299
15 more
  1. 2021Monash Time Series Forecasting Archivecited by 256
  2. 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variablescited by 241
  3. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  4. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 188
  5. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  6. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  7. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  8. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  9. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 88
  10. 2023AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecastingcited by 36
  11. 2024Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecastingcited by 18
  12. 2024Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Modelscited by 10
  13. 2013Aggregation of Affine Estimatorscited by 4
  14. 2020An Accurate and Fully-Automated Ensemble Model for Weekly Time Series Forecastingcited by 4
  15. 2025N-BEATS-MOE: N-BEATS with a Mixture-of-Experts Layer for Heterogeneous Time Series Forecastingcited by 1

Built on by

Not cited yet.