PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting

• URL: http://arxiv.org/abs/2310.00655v2
• Date: Sun, 13 Oct 2024 09:35:48 GMT
• Title: PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
• Authors: Zeying Gong, Yujin Tang, Junwei Liang,
• Abstract summary: 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.
• Score: 3.7244649185886978
• License:
• Abstract: Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads to a loss of temporal information. To tackle these challenges, we propose PatchMixer, a novel CNN-based model. It introduces a permutation-variant convolutional structure to preserve temporal information. Diverging from conventional CNNs in this field, which often employ multiple scales or numerous branches, our method relies exclusively on depthwise separable convolutions. This allows us to extract both local features and global correlations using a single-scale architecture. Furthermore, we employ dual forecasting heads encompassing linear and nonlinear components to better model future curve trends and details. Our experimental results on seven time-series forecasting benchmarks indicate that compared with the state-of-the-art method and the best-performing CNN, PatchMixer yields $3.9\%$ and $21.2\%$ relative improvements, respectively, while being 2-3x faster than the most advanced method.

Related papers

• 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)
• Are Self-Attentions Effective for Time Series Forecasting? [4.990206466948269]
  Time series forecasting is crucial for applications across multiple domains and various scenarios. Recent findings have indicated that simpler linear models might outperform complex Transformer-based approaches. We introduce a new architecture, Cross-Attention-only Time Series transformer (CATS) Our model achieves superior performance with the lowest mean squared error and uses fewer parameters compared to existing models.
  arXiv  Detail & Related papers  (2024-05-27T06:49:39Z)
• 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)
• 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)
• MultiResFormer: Transformer with Adaptive Multi-Resolution Modeling for General Time Series Forecasting [18.990322695844675]
  Transformer-based models have greatly pushed the boundaries of time series forecasting recently. Existing methods typically encode time series data into $textitpatches$ using one or a fixed set of patch lengths. We propose MultiResFormer, which dynamically models temporal variations by adaptively choosing optimal patch lengths.
  arXiv  Detail & Related papers  (2023-11-30T18:24:33Z)
• 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)
• CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting [50.23240107430597]
  We design a special Transformer, i.e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue.
  arXiv  Detail & Related papers  (2023-05-20T05:16:31Z)
• FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification [53.55504611255664]
  FormerTime is a hierarchical representation model for improving the classification capacity for the multivariate time series classification task. It exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism.
  arXiv  Detail & Related papers  (2023-02-20T07:46:14Z)
• Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer Architectures [1.278093617645299]
  This study focuses on multi-step-temporal wind speed forecasting for the Norwegian continental shelf. A graph neural network (GNN) architecture was used to extract spatial dependencies, with different update functions to learn temporal correlations. This is the first time the LogSparse Transformer and Autoformer have been applied to wind forecasting.
  arXiv  Detail & Related papers  (2022-08-29T13:26:20Z)
• A Differential Attention Fusion Model Based on Transformer for Time Series Forecasting [4.666618110838523]
  Time series forecasting is widely used in the fields of equipment life cycle forecasting, weather forecasting, traffic flow forecasting, and other fields. Some scholars have tried to apply Transformer to time series forecasting because of its powerful parallel training ability. The existing Transformer methods do not pay enough attention to the small time segments that play a decisive role in prediction.
  arXiv  Detail & Related papers  (2022-02-23T10:33:12Z)

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.