A Simplified Pytorch implementation of the Diffusion Convolutional Recurrent Neural Network: Yaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu, Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, ICLR 2018.
This repo is self-implemented under the help of the original tensorflow implementaion and a third party pytorch implementation. The motivation of this implementation is to build a simple and user-friendly reference for learners and practitioners in the Graph-based Spatial-Temporal data mining area.
If you are interested in the area, you could further check our paper about passenger demand forecasting: "STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting"