Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting

• URL: http://arxiv.org/abs/2601.12467v2
• Date: Wed, 21 Jan 2026 14:41:56 GMT
• Title: Patch-Level Tokenization with CNN Encoders and Attention for Improved Transformer Time-Series Forecasting
• Authors: Saurish Nagrath, Saroj Kumar Panigrahy,
• Abstract summary: This paper proposes a two-stage forecasting framework that separates local temporal representation learning from global dependency modelling.<n>A convolutional neural network operates on fixed-length temporal patches to extract short-range temporal dynamics and non-linear feature interactions.<n> Token-level self-attention is applied during representation learning to refine these embeddings, after which a Transformer encoder models inter-patch temporal dependencies to generate forecasts.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformer-based models have shown strong performance in time-series forecasting by leveraging self-attention to model long-range temporal dependencies. However, their effectiveness depends critically on the quality and structure of input representations derived from raw multivariate time-series data, particularly as sequence length and data scale increase. This paper proposes a two-stage forecasting framework that explicitly separates local temporal representation learning from global dependency modelling. In the proposed approach, a convolutional neural network operates on fixed-length temporal patches to extract short-range temporal dynamics and non-linear feature interactions, producing compact patch-level token embeddings. Token-level self-attention is applied during representation learning to refine these embeddings, after which a Transformer encoder models inter-patch temporal dependencies to generate forecasts. The method is evaluated on a synthetic multivariate time-series dataset with controlled static and dynamic factors, using an extended sequence length and a larger number of samples. Experimental results demonstrate that the proposed framework consistently outperforms a convolutional baseline under increased temporal context and remains competitive with a strong patch-based Transformer model. These findings indicate that structured patch-level tokenization provides a scalable and effective representation for multivariate time-series forecasting, particularly when longer input sequences are considered.

Related papers

• DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters [50.43534351968113]
  Existing generative time series models do not address the multi-dimensional properties of time series data well.<n>Inspired by Multimodal Diffusion Transformers that integrate textual guidance into video generation, we propose Diffusion Transformers for Time Series (DiTS)
  arXiv  Detail & Related papers  (2026-02-06T10:48:13Z)
• A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting [81.73338008264115]
  Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers.<n>We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series.<n>Fire consistently outperforms state-of-the-art models on long-term forecasting benchmarks.
  arXiv  Detail & Related papers  (2025-10-11T09:59:25Z)
• TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting [18.890651211582256]
  We develop a novel Transformer architecture designed for time series data, aiming to maximize its representational capacity.<n>We identify two key but often overlooked characteristics of time series: (1) unidirectional influence from the past to the future, and (2) the phenomenon of decaying influence over time.<n>We propose TimeFormer, whose core innovation is a self-attention mechanism with two modulation terms (MoSA), designed to capture these temporal priors of time series.
  arXiv  Detail & Related papers  (2025-10-08T06:07:30Z)
• 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)
• Sentinel: Multi-Patch Transformer with Temporal and Channel Attention for Time Series Forecasting [48.52101281458809]
  Transformer-based time series forecasting has recently gained strong interest due to the ability of transformers to model sequential data.<n>We propose Sentinel, a transformer-based architecture composed of an encoder able to extract contextual information from the channel dimension.<n>We introduce a multi-patch attention mechanism, which leverages the patching process to structure the input sequence in a way that can be naturally integrated into the transformer architecture.
  arXiv  Detail & Related papers  (2025-03-22T06:01:50Z)
• PSformer: Parameter-efficient Transformer with Segment Attention for Time Series Forecasting [21.033660755921737]
  Time forecasting remains a critical challenge across various domains, often complicated by high-dimensional data and long-term dependencies.<n>This paper presents a novel transformer architecture for time series forecasting, incorporating two key innovations: parameter sharing (PS) and Spatial-Temporal Attention (SegAtt)
  arXiv  Detail & Related papers  (2024-11-03T03:04:00Z)
• 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)
• PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting [82.03373838627606]
  Self-attention mechanism in Transformer architecture requires positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embeddings restricts the Transformer's ability to effectively represent temporal sequences. We present a model integrating PRE with a standard Transformer encoder, demonstrating state-of-the-art performance on various real-world datasets.
  arXiv  Detail & Related papers  (2024-08-20T01:56:07Z)
• Advancing Long-Term Multi-Energy Load Forecasting with Patchformer: A Patch and Transformer-Based Approach [1.4228349888743608]
  This paper introduces Patchformer, a novel model that integrates patch embedding with encoder-decoder Transformer-based architectures. Patchformer is illustrated as the only model that follows the positive correlation between model performance and the length of the past sequence.
  arXiv  Detail & Related papers  (2024-04-16T10:56:33Z)
• Rough Transformers for Continuous and Efficient Time-Series Modelling [46.58170057001437]
  Time-series data in real-world medical settings typically exhibit long-range dependencies and are observed at non-uniform intervals. We introduce the Rough Transformer, a variation of the Transformer model which operates on continuous-time representations of input sequences. We find that Rough Transformers consistently outperform their vanilla attention counterparts while obtaining the benefits of Neural ODE-based models.
  arXiv  Detail & Related papers  (2024-03-15T13:29:45Z)
• 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)
• Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning [22.28251586213348]
  aLLM4TS is an innovative framework that adapts Large Language Models (LLMs) for time-series representation learning. A distinctive element of our framework is the patch-wise decoding layer, which departs from previous methods reliant on sequence-level decoding.
  arXiv  Detail & Related papers  (2024-02-07T13:51:26Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System [46.39662315849883]
  We introduce CLMFormer, a novel framework that mitigates redundancy through curriculum learning and a memory-driven decoder.<n>CLMFormer consistently improves Transformer-based models by up to 30%, demonstrating its effectiveness in long-horizon forecasting.
  arXiv  Detail & Related papers  (2022-07-16T04:05:15Z)
• DRAformer: Differentially Reconstructed Attention Transformer for Time-Series Forecasting [7.805077630467324]
  Time-series forecasting plays an important role in many real-world scenarios, such as equipment life cycle forecasting, weather forecasting, and traffic flow forecasting. It can be observed from recent research that a variety of transformer-based models have shown remarkable results in time-series forecasting. However, there are still some issues that limit the ability of transformer-based models on time-series forecasting tasks.
  arXiv  Detail & Related papers  (2022-06-11T10:34:29Z)
• 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.