LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting

• URL: http://arxiv.org/abs/2403.16495v1
• Date: Mon, 25 Mar 2024 07:23:23 GMT
• Title: LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• Authors: Qinyao Luo, Silu He, Xing Han, Yuhan Wang, Haifeng Li,
• Abstract summary: Long-term Transformer-based Network (LSTTN) is proposed to learn long- and short-term representations of historical traffic flow. LSTTN fuses the long-term trend, periodic features and short-term features to obtain the prediction results. In experiments, LSTTN achieves a minimum of 5.63% improvement and a maximum improvement of 16.78% over baseline models.
• Score: 4.913321495945671
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate traffic forecasting is a fundamental problem in intelligent transportation systems and learning long-range traffic representations with key information through spatiotemporal graph neural networks (STGNNs) is a basic assumption of current traffic flow prediction models. However, due to structural limitations, existing STGNNs can only utilize short-range traffic flow data; therefore, the models cannot adequately learn the complex trends and periodic features in traffic flow. Besides, it is challenging to extract the key temporal information from the long historical traffic series and obtain a compact representation. To solve the above problems, we propose a novel LSTTN (Long-Short Term Transformer-based Network) framework comprehensively considering the long- and short-term features in historical traffic flow. First, we employ a masked subseries Transformer to infer the content of masked subseries from a small portion of unmasked subseries and their temporal context in a pretraining manner, forcing the model to efficiently learn compressed and contextual subseries temporal representations from long historical series. Then, based on the learned representations, long-term trend is extracted by using stacked 1D dilated convolution layers, and periodic features are extracted by dynamic graph convolution layers. For the difficulties in making time-step level prediction, LSTTN adopts a short-term trend extractor to learn fine-grained short-term temporal features. Finally, LSTTN fuses the long-term trend, periodic features and short-term features to obtain the prediction results. Experiments on four real-world datasets show that in 60-minute-ahead long-term forecasting, the LSTTN model achieves a minimum improvement of 5.63\% and a maximum improvement of 16.78\% over baseline models. The source code is available at https://github.com/GeoX-Lab/LSTTN.

Related papers

• 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)
• HUTFormer: Hierarchical U-Net Transformer for Long-Term Traffic Forecasting [13.49661832917228]
  We make the first attempt to explore long-term traffic forecasting, e.g., 1-day forecasting. We propose a novel Hierarchical U-net TransFormer to address the issues of long-term traffic forecasting. The proposed HUTFormer significantly outperforms state-of-the-art traffic forecasting and long time series forecasting baselines.
  arXiv  Detail & Related papers  (2023-07-27T02:43:21Z)
• 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)
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction [78.05103666987655]
  spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. We propose a novel propagation delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency.
  arXiv  Detail & Related papers  (2023-01-19T08:42:40Z)
• 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)
• STGIN: A Spatial Temporal Graph-Informer Network for Long Sequence Traffic Speed Forecasting [8.596556653895028]
  This study proposes a new spatial-temporal neural network architecture to handle the long-term traffic parameters forecasting issue. The attention mechanism potentially guarantees long-term prediction performance without significant information loss from distant inputs.
  arXiv  Detail & Related papers  (2022-10-01T05:58:22Z)
• Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting [13.441945545904504]
  We propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP) Specifically, we design a pre-training model to efficiently learn temporal patterns from very long-term history time series. Our framework is capable of significantly enhancing downstream STGNNs, and our pre-training model aptly captures temporal patterns.
  arXiv  Detail & Related papers  (2022-06-18T04:24:36Z)
• STformer: A Noise-Aware Efficient Spatio-Temporal Transformer Architecture for Traffic Forecasting [7.230415327436048]
  We propose a novel noise-aware efficient-temporal architecture for accurate traffic forecasting, named STformer. STformer consists of two components, which are the noise-aware temporal self-attention (NATSA) and the graph-based sparse spatial self-attention (GBS3A) Experiments on four real-world traffic datasets show that STformer outperforms state-of-the-art baselines with lower computational cost.
  arXiv  Detail & Related papers  (2021-12-06T02:17:39Z)
• Online learning of windmill time series using Long Short-term Cognitive Networks [58.675240242609064]
  The amount of data generated on windmill farms makes online learning the most viable strategy to follow. We use Long Short-term Cognitive Networks (LSTCNs) to forecast windmill time series in online settings. Our approach reported the lowest forecasting errors with respect to a simple RNN, a Long Short-term Memory, a Gated Recurrent Unit, and a Hidden Markov Model.
  arXiv  Detail & Related papers  (2021-07-01T13:13:24Z)
• Unified Spatio-Temporal Modeling for Traffic Forecasting using Graph Neural Network [2.7088996845250897]
  We argue that temporal is less effective to extract the complex-temporal relationship with such factorized modules. We propose a Unified S-weekly Graph Convolution (USTGCN) for traffic forecasting that performs both spatial and temporal aggregation. Our model USTGCN can outperform state-of-the-art performances in three popular benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T12:33:17Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

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.