Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data
arXiv:1804.00684
Abstract
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time. Our multi-scaled framework is a seamless coupling of two major components: a self-exciting point process that models the macroscale statistical behaviors of the ST data and a graph structured recurrent neural network (GSRNN) to discover the microscale patterns of the ST data on the inferred graph. This novel deep neural network (DNN) incorporates the real time interactions of the graph nodes to enable more accurate real time forecasting. The effectiveness of our method is demonstrated on both crime and traffic forecasting.
9 pages, 19 figures
References in corpus (2)
Cited by in corpus (14)
- Graph Neural Network for Traffic Forecasting: A Survey
- Deep Learning for Spatio-Temporal Data Mining: A Survey
- Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
- Modeling of Spatio-Temporal Hawkes Processes with Randomized Kernels
- Deep Learning-Based Spatiotemporal Multi-Event Reconstruction for Delay Line Detectors
- A Study of Joint Graph Inference and Forecasting
- RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Framework
- Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction
- A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
- A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
- A Spatial-Temporal Graph Based Hybrid Infectious Disease Model with Application to COVID-19
- Graph Deep Factors for Forecasting
- Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
- Prediction with Spatio-temporal Point Processes with Self Organizing Decision Trees