Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting

• URL: http://arxiv.org/abs/2502.06151v1
• Date: Mon, 10 Feb 2025 04:42:11 GMT
• Title: Powerformer: A Transformer with Weighted Causal Attention for Time-series Forecasting
• Authors: Kareem Hegazy, Michael W. Mahoney, N. Benjamin Erichson,
• Abstract summary: We introduce Powerformer, a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay. Our empirical results demonstrate that Powerformer achieves state-of-the-art accuracy on public time-series benchmarks. Our analyses show that the model's locality bias is amplified during training, demonstrating an interplay between time-series data and power-law-based attention.
• Score: 50.298817606660826
• License:
• Abstract: Transformers have recently shown strong performance in time-series forecasting, but their all-to-all attention mechanism overlooks the (temporal) causal and often (temporally) local nature of data. We introduce Powerformer, a novel Transformer variant that replaces noncausal attention weights with causal weights that are reweighted according to a smooth heavy-tailed decay. This simple yet effective modification endows the model with an inductive bias favoring temporally local dependencies, while still allowing sufficient flexibility to learn the unique correlation structure of each dataset. Our empirical results demonstrate that Powerformer not only achieves state-of-the-art accuracy on public time-series benchmarks, but also that it offers improved interpretability of attention patterns. Our analyses show that the model's locality bias is amplified during training, demonstrating an interplay between time-series data and power-law-based attention. These findings highlight the importance of domain-specific modifications to the Transformer architecture for time-series forecasting, and they establish Powerformer as a strong, efficient, and principled baseline for future research and real-world applications.

Related papers

• ExoTST: Exogenous-Aware Temporal Sequence Transformer for Time Series Prediction [11.511830352094353]
  We propose ExoTST, a transformer-based framework for time series prediction. To integrate past and current variables, ExoTST introduces a novel cross-temporal modality fusion module. Experiments on real-world carbon flux datasets and time series benchmarks demonstrate ExoTST's superior performance.
  arXiv  Detail & Related papers  (2024-10-16T03:04:37Z)
• TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables [75.83318701911274]
  TimeXer ingests external information to enhance the forecasting of endogenous variables. TimeXer achieves consistent state-of-the-art performance on twelve real-world forecasting benchmarks.
  arXiv  Detail & Related papers  (2024-02-29T11:54:35Z)
• 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)
• Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach [71.67506068703314]
  Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services. Traditionally, urban mobility data has been structured as videos, treating longitude and latitude as fundamental pixels. In our research, we introduce a fresh perspective on urban mobility prediction. Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex time series.
  arXiv  Detail & Related papers  (2023-12-04T07:39:05Z)
• Two Steps Forward and One Behind: Rethinking Time Series Forecasting with Deep Learning [7.967995669387532]
  The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks. We investigate the effectiveness of Transformer-based models applied to the domain of time series forecasting. We propose a set of alternative models that are better performing and significantly less complex.
  arXiv  Detail & Related papers  (2023-04-10T12:47:42Z)
• 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)
• Robust representations of oil wells' intervals via sparse attention mechanism [2.604557228169423]
  We introduce the class of efficient Transformers named Regularized Transformers (Reguformers) The focus in our experiments is on oil&gas data, namely, well logs. To evaluate our models for such problems, we work with an industry-scale open dataset consisting of well logs of more than 20 wells.
  arXiv  Detail & Related papers  (2022-12-29T09:56:33Z)
• Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting [86.33543833145457]
  We propose Non-stationary Transformers as a generic framework with two interdependent modules: Series Stationarization and De-stationary Attention. Our framework consistently boosts mainstream Transformers by a large margin, which reduces MSE by 49.43% on Transformer, 47.34% on Informer, and 46.89% on Reformer.
  arXiv  Detail & Related papers  (2022-05-28T12:27:27Z)
• TACTiS: Transformer-Attentional Copulas for Time Series [76.71406465526454]
  estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. We propose a versatile method that estimates joint distributions using an attention-based decoder. We show that our model produces state-of-the-art predictions on several real-world datasets.
  arXiv  Detail & Related papers  (2022-02-07T21:37:29Z)
• ETSformer: Exponential Smoothing Transformers for Time-series Forecasting [35.76867542099019]
  We propose ETSFormer, a novel time-series Transformer architecture, which exploits the principle of exponential smoothing in improving Transformers for time-series forecasting. In particular, inspired by the classical exponential smoothing methods in time-series forecasting, we propose the novel exponential smoothing attention (ESA) and frequency attention (FA) to replace the self-attention mechanism in vanilla Transformers, thus improving both accuracy and efficiency.
  arXiv  Detail & Related papers  (2022-02-03T02:50:44Z)

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.