Spatio-Temporal Meta Learning for Urban Traffic Prediction

Pan, Zheyi; Zhang, Wentao; Liang, Yuxuan; Zhang, Weinan; Yu, Yong; Zhang, Junbo; Zheng, Yu

doi:10.1109/tkde.2020.2995855

Cited by 97 publications

(41 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MTS forecasting, which aims at forecasting the future trends based on a group of historical observed time series, has been widely studied in recent years. It is of great importance in a wide range of applications, e.g., a better driving route can be planned in advance based on the forecasted traffic flows, and an investment strategy can be designed with the forecasting of the near-future stock market [2]- [5].…”

Section: Introductionmentioning

confidence: 99%

Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting

Chen¹,

Chen²,

Shang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multivariate time series (MTS) forecasting plays an important role in the automation and optimization of intelligent applications. It is a challenging task, as we need to consider both complex intra-variable dependencies and inter-variable dependencies. Existing works only learn temporal patterns with the help of single inter-variable dependencies. However, there are multi-scale temporal patterns in many real-world MTS. Single inter-variable dependencies make the model prefer to learn one type of prominent and shared temporal patterns. In this paper, we propose a multi-scale adaptive graph neural network (MAGNN) to address the above issue. MAGNN exploits a multiscale pyramid network to preserve the underlying temporal dependencies at different time scales. Since the inter-variable dependencies may be different under distinct time scales, an adaptive graph learning module is designed to infer the scalespecific inter-variable dependencies without pre-defined priors. Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies. After that, we develop a scale-wise fusion module to effectively promote the collaboration across different time scales, and automatically capture the importance of contributed temporal patterns. Experiments on four real-world datasets demonstrate that MAGNN outperforms the state-of-the-art methods across various settings.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting

Chen¹,

Chen²,

Shang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Other work leverages the ConvLSTM network both for forecasting (e.g., [24,25] and for fine-scale prediction (e.g., [26]). In addition, attention-based approaches also capture the spatial relationships by learning the attention score for the observed locations to predict for the target locations [27,28]. However, these approaches usually require large amounts of evenly distributed labeled data to achieve good performance, especially for the prediction tasks.…”

Section: Resultsmentioning

confidence: 99%

Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction

Lin

Chiang

Franklin

et al. 2020

2020 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

Many scientific prediction problems have spatiotemporal data-and modeling-related challenges in handling complex variations in space and time using only sparse and unevenly distributed observations. This paper presents a novel deep learning architecture, Deep learning predictions for LocATion-dependent Time-sEries data (DeepLATTE), that explicitly incorporates theories of spatial statistics into neural networks to addresses these challenges. In addition to a feature selection module and a spatiotemporal learning module, DeepLATTE contains an autocorrelation-guided semi-supervised learning strategy to enforce both local autocorrelation patterns and global autocorrelation trends of the predictions in the learned spatiotemporal embedding space to be consistent with the observed data, overcoming the limitation of sparse and unevenly distributed observations. During the training process, both supervised and semi-supervised losses guide the updates of the entire network to: 1) prevent overfitting, 2) refine feature selection, 3) learn useful spatiotemporal representations, and 4) improve overall prediction. We conduct a demonstration of DeepLATTE using publicly available data for an important public health topic, air quality prediction, in a well-studied, complex physical environment -Los Angeles. The experiment demonstrates that the proposed approach provides accurate fine-spatial-scale air quality predictions and reveals the critical environmental factors affecting the results.

show abstract

“…• Graph WaveNet [13]: It exploits graph convolution operations and WaveNet to model spatial and temporal correlations, respectively. • ST-MetaNet [40]: A meta learning based spatial-temporal network, which consists two types of meta networks: meta graph attention network and meta recurrent neural network.…”

Section: B Methods For Comparisonmentioning

confidence: 99%

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Chen¹,

Chen²,

Shang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

show abstract

Spatio-Temporal Meta Learning for Urban Traffic Prediction

Cited by 97 publications

References 32 publications

Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting

Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting

Building Autocorrelation-Aware Representations for Fine-Scale Spatiotemporal Prediction

Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting

Contact Info

Product

Resources

About