We propose a novel deep learning framework, STGCN, to tackle time series prediction problem in traffic domain. Instead of applying regular convolutional and recurrent units, we formulate the problem ...

Abstract: Graph representation learning (GRL) is fundamental in multi-graph applications like molecular property prediction. Graph neural networks (GNNs) have emerged as a popular method for GRL.

Abstract: Computer-Aided Design (CAD) sketches, composed of geometric primitives and constraints, are fundamental to CAD models and play a critical role in industrial design and manufacturing.