# Preserving Dynamic Attention for Long-Term Spatial-Temporal Prediction

arXiv: https://arxiv.org/abs/2006.08849 · HTML: https://mlsanity.com/paper/2006.08849/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2020.

## Built on by (most cited first, 30 of 30)

- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2301.07945/) (2023)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Quantifying Uncertainty in Deep Spatiotemporal Forecasting](https://mlsanity.com/paper/2105.11982/) (2021)
- [Meta-Learning Dynamics Forecasting Using Task Inference](https://mlsanity.com/paper/2102.10271/) (2021)
- [TimeX++: Learning Time-Series Explanations with Information Bottleneck](https://mlsanity.com/paper/2405.09308/) (2024)
- [Automated Spatio-Temporal Graph Contrastive Learning](https://mlsanity.com/paper/2305.03920/) (2023)
- [Explaining Time Series via Contrastive and Locally Sparse Perturbations](https://mlsanity.com/paper/2401.08552/) (2024)
- [LibCity: A Unified Library Towards Efficient and Comprehensive Urban Spatial-Temporal Prediction](https://mlsanity.com/paper/2304.14343/) (2023)
- [Interpretation of Time-Series Deep Models: A Survey](https://mlsanity.com/paper/2305.14582/) (2023)
- [Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting](https://mlsanity.com/paper/2205.08689/) (2022)
- [A Lightweight and Accurate Spatial-Temporal Transformer for Traffic Forecasting](https://mlsanity.com/paper/2201.00008/) (2021)
- [Deep Bayesian Active Learning for Accelerating Stochastic Simulation](https://mlsanity.com/paper/2106.02770/) (2021)
- [A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management](https://mlsanity.com/paper/2306.02806/) (2023)
- [MSGNN: Multi-scale Spatio-temporal Graph Neural Network for Epidemic Forecasting](https://mlsanity.com/paper/2308.15840/) (2023)
- [Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach](https://mlsanity.com/paper/2312.01699/) (2023)
- [CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent System](https://mlsanity.com/paper/2405.14691/) (2024)
- [DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction](https://mlsanity.com/paper/2108.08170/) (2021)
- [Unified Data Management and Comprehensive Performance Evaluation for Urban Spatial-Temporal Prediction [Experiment, Analysis & Benchmark]](https://mlsanity.com/paper/2308.12899/) (2023)
- [Enhancing Topological Dependencies in Spatio-Temporal Graphs with Cycle Message Passing Blocks](https://mlsanity.com/paper/2401.15894/) (2024)
- [Leveraging Intra-Period and Inter-Period Features for Enhanced Passenger Flow Prediction of Subway Stations](https://mlsanity.com/paper/2410.14727/) (2024)
- [Exploring Context Generalizability in Citywide Crowd Mobility Prediction: An Analytic Framework and Benchmark](https://mlsanity.com/paper/2106.16046/) (2021)
- [ARMA Cell: A Modular and Effective Approach for Neural Autoregressive Modeling](https://mlsanity.com/paper/2208.14919/) (2022)
- [STContext: A Multifaceted Dataset for Developing Context-aware Spatio-temporal Crowd Mobility Prediction Models](https://mlsanity.com/paper/2501.03583/) (2025)
- [UrbanFM: Scaling Urban Spatio-Temporal Foundation Models](https://mlsanity.com/paper/2602.20677/) (2026)
- [ARFA: An Asymmetric Receptive Field Autoencoder Model for Spatiotemporal Prediction](https://mlsanity.com/paper/2309.00314/) (2023)
- [PASTA: PArallel Spatio-Temporal Attention with spatial auto-correlation gating for fine-grained crowd flow prediction](https://mlsanity.com/paper/2310.02284/) (2023)
- [Transport-Hub-Aware Spatial-Temporal Adaptive Graph Transformer for Traffic Flow Prediction](https://mlsanity.com/paper/2310.08328/) (2023)
- [Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecasting](https://mlsanity.com/paper/2509.00515/) (2025)
- [Capturing Complex Spatial-Temporal Dependencies in Traffic Forecasting: A Self-Attention Approach](https://mlsanity.com/paper/2511.07980/) (2025)

## Abstract (arXiv)

Effective long-term predictions have been increasingly demanded in urban-wise data mining systems. Many practical applications, such as accident prevention and resource pre-allocation, require an extended period for preparation. However, challenges come as long-term prediction is highly error-sensitive, which becomes more critical when predicting urban-wise phenomena with complicated and dynamic spatial-temporal correlation. Specifically, since the amount of valuable correlation is limited, enormous irrelevant features introduce noises that trigger increased prediction errors. Besides, after each time step, the errors can traverse through the correlations and reach the spatial-temporal positions in every future prediction, leading to significant error propagation. To address these issues, we propose a Dynamic Switch-Attention Network (DSAN) with a novel Multi-Space Attention (MSA) mechanism that measures the correlations between inputs and outputs explicitly. To filter out irrelevant noises and alleviate the error propagation, DSAN dynamically extracts valuable information by applying self-attention over the noisy input and bridges each output directly to the purified inputs via implementing a switch-attention mechanism. Through extensive experiments on two spatial-temporal prediction tasks, we demonstrate the superior advantage of DSAN in both short-term and long-term predictions.