STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction
This addresses metro ridership prediction for governments and researchers, offering an incremental improvement over existing graph convolutional recurrent networks.
The authors tackled metro ridership prediction by proposing STR-GODEs, a model that learns spatial, temporal, and ridership correlations without equal time intervals, reducing error accumulation in long series; experiments on two large-scale datasets showed efficacy and robustness.
The metro ridership prediction has always received extensive attention from governments and researchers. Recent works focus on designing complicated graph convolutional recurrent network architectures to capture spatial and temporal patterns. These works extract the information of spatial dimension well, but the limitation of temporal dimension still exists. We extended Neural ODE algorithms to the graph network and proposed the STR-GODEs network, which can effectively learn spatial, temporal, and ridership correlations without the limitation of dividing data into equal-sized intervals on the timeline. While learning the spatial relations and the temporal correlations, we modify the GODE-RNN cell to obtain the ridership feature and hidden states. Ridership information and its hidden states are added to the GODESolve to reduce the error accumulation caused by long time series in prediction. Extensive experiments on two large-scale datasets demonstrate the efficacy and robustness of our model.