Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning

• URL: http://arxiv.org/abs/2206.12126v3
• Date: Wed, 12 Apr 2023 08:08:50 GMT
• Title: Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
• Authors: Cheng Tan, Zhangyang Gao, Lirong Wu, Yongjie Xu, Jun Xia, Siyuan Li, Stan Z. Li
• Abstract summary: We present a general framework of predictive learning, in which the encoder and decoder capture intra-frame features and the middle temporal module catches inter-frame dependencies. To parallelize the temporal module, we propose the Temporal Attention Unit (TAU), which decomposes the temporal attention into intraframe statical attention and inter-frame dynamical attention.
• Score: 42.22064610886404
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial encoder and decoder capture intra-frame features and the middle temporal module catches inter-frame correlations. While the mainstream methods employ recurrent units to capture long-term temporal dependencies, they suffer from low computational efficiency due to their unparallelizable architectures. To parallelize the temporal module, we propose the Temporal Attention Unit (TAU), which decomposes the temporal attention into intra-frame statical attention and inter-frame dynamical attention. Moreover, while the mean squared error loss focuses on intra-frame errors, we introduce a novel differential divergence regularization to take inter-frame variations into account. Extensive experiments demonstrate that the proposed method enables the derived model to achieve competitive performance on various spatiotemporal prediction benchmarks.

Related papers

• STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing [6.872340834265972]
  We propose STLight, a novel method for S-temporal learning that relies solely on channel-wise and depth-wise convolutions as learnable layers. STLight overcomes the limitations of traditional convolutional approaches by rearranging spatial and temporal dimensions together. Our architecture achieves state-of-the-art performance on STL benchmarks across datasets and settings, while significantly improving computational efficiency in terms of parameters and computational FLOPs.
  arXiv  Detail & Related papers  (2024-11-15T13:53:19Z)
• Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting [16.782154479264126]
  Predicting backbone-temporal traffic flow presents challenges due to complex interactions between temporal factors. Existing approaches address these dimensions in isolation, neglecting their critical interdependencies. In this paper, we introduce Sanonymous-Temporal Unitized Unitized Cell (ASTUC), a unified framework designed to capture both spatial and temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-14T07:34:31Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• 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)
• Triplet Attention Transformer for Spatiotemporal Predictive Learning [9.059462850026216]
  We propose an innovative triplet attention transformer designed to capture both inter-frame dynamics and intra-frame static features. The model incorporates the Triplet Attention Module (TAM), which replaces traditional recurrent units by exploring self-attention mechanisms in temporal, spatial, and channel dimensions.
  arXiv  Detail & Related papers  (2023-10-28T12:49:33Z)
• Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning under A Unified View [73.73667848619343]
  We introduce USTEP (Unified S-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales.
  arXiv  Detail & Related papers  (2023-10-09T16:17:42Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version [37.09531298150374]
  Traffic series forecasting is challenging due to complex time series patterns for the same time series patterns may vary across time, where, for example, there exist periods across a day showing stronger temporal correlations. Such-temporal models employ a shared parameter space irrespective of the time locations and the time periods and they assume that the temporal correlations are similar across locations and do not always hold across time which may not always be the case. We propose a framework that aims at turning ICD-temporal aware models to encode sub-temporal models.
  arXiv  Detail & Related papers  (2022-03-29T16:44:56Z)
• Supporting Optimal Phase Space Reconstructions Using Neural Network Architecture for Time Series Modeling [68.8204255655161]
  We propose an artificial neural network with a mechanism to implicitly learn the phase spaces properties. Our approach is either as competitive as or better than most state-of-the-art strategies.
  arXiv  Detail & Related papers  (2020-06-19T21:04:47Z)

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.