PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting

• URL: http://arxiv.org/abs/2601.20845v1
• Date: Wed, 28 Jan 2026 18:45:45 GMT
• Title: PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting
• Authors: Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz,
• Abstract summary: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance.<n>We introduce PatchFormer, a patch-based time series foundation model that uses hierarchical masked reconstruction for self-supervised pretraining.<n> Experiments on 24 benchmark datasets spanning weather, energy, traffic, finance, and healthcare demonstrate state-of-the-art zero-shot multi-horizon forecasting.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require domain-specific feature engineering and substantial labeled data for each task. We introduce PatchFormer, a patch-based time series foundation model that uses hierarchical masked reconstruction for self-supervised pretraining and lightweight adapters for efficient transfer. PatchFormer segments time series into patches and learns multiscale temporal representations with learnable aggregation across temporal scales. Pretraining uses masked patch reconstruction with dynamic masking and objectives that encourage both local accuracy and global consistency, followed by cross-domain knowledge distillation. Experiments on 24 benchmark datasets spanning weather, energy, traffic, finance, and healthcare demonstrate state-of-the-art zero-shot multi-horizon forecasting, reducing mean squared error by 27.3 percent relative to strong baselines while requiring 94 percent less task-specific training data. The model exhibits near log-linear scaling with more pretraining data up to 100 billion points and processes length-512 sequences 3.8x faster than full-sequence transformers.

Related papers

• EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting [50.794700596484894]
  We propose EntroPE (Entropy-Guided Dynamic Patch), a novel, temporally informed framework that dynamically detects transition points via conditional entropy.<n>This preserves temporal structure while retaining the computational benefits of patching.<n> Experiments across long-term forecasting benchmarks demonstrate that EntroPE improves both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-09-30T12:09:56Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Towards Generalisable Time Series Understanding Across Domains [10.350643783811174]
  We introduce a novel pre-training paradigm specifically designed to handle time series heterogeneity.<n>We propose a tokeniser with learnable domain signatures, a dual masking strategy, and a normalised cross-correlation loss.<n>Our code and pre-trained weights are available at https://www.oetu.com/oetu/otis.
  arXiv  Detail & Related papers  (2024-10-09T17:09:30Z)
• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• 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)
• Attention as Robust Representation for Time Series Forecasting [23.292260325891032]
  Time series forecasting is essential for many practical applications. Transformers' key feature, the attention mechanism, dynamically fusing embeddings to enhance data representation, often relegating attention weights to a byproduct role. Our approach elevates attention weights as the primary representation for time series, capitalizing on the temporal relationships among data points to improve forecasting accuracy.
  arXiv  Detail & Related papers  (2024-02-08T03:00:50Z)
• Unified Training of Universal Time Series Forecasting Transformers [104.56318980466742]
  We present a Masked-based Universal Time Series Forecasting Transformer (Moirai) Moirai is trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains. Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models.
  arXiv  Detail & Related papers  (2024-02-04T20:00:45Z)
• TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling [67.02157180089573]
  Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. This paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks.
  arXiv  Detail & Related papers  (2024-02-04T13:10:51Z)
• PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting [3.7244649185886978]
  We propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Compared with the state-of-the-art method and the best-performing CNN, PatchMixer yields $3.9%$ and $21.2%$ relative improvements.
  arXiv  Detail & Related papers  (2023-10-01T12:47:59Z)
• Ti-MAE: Self-Supervised Masked Time Series Autoencoders [16.98069693152999]
  We propose a novel framework named Ti-MAE, in which the input time series are assumed to follow an integrate distribution. Ti-MAE randomly masks out embedded time series data and learns an autoencoder to reconstruct them at the point-level. Experiments on several public real-world datasets demonstrate that our framework of masked autoencoding could learn strong representations directly from the raw data.
  arXiv  Detail & Related papers  (2023-01-21T03:20:23Z)
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers [4.635547236305835]
  We propose an efficient design of Transformer-based models for time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer. PatchTST can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models.
  arXiv  Detail & Related papers  (2022-11-27T05:15:42Z)

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.