IEEE

Explanations for Graph Neural Networks using A Game-theoretic Value

Abstract: Graph Neural Networks (GNNs) have achieved remarkable performance on various learning tasks on geometric data. However, the incorporation of graph structures into the learning of node ...
IEEE

Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions

Abstract: Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph ...
GitHub

SizheHu/Raster-to-Graph

Raster-to-Graph is a novel automatic recognition framework, which achieves structural and semantic recognition of floorplans, addresses the problem of obtaining high-quality vectorized floorplans from ...
GitHub

Pre-training-Enhanced Spatial-Temporal Graph Neural Network For Multivariate Time Series Forecasting

Code for our SIGKDD'22 paper: "Pre-training-Enhanced Spatial-Temporal Graph Neural Network For Multivariate Time Series Forecasting". The code is developed with BasicTS, a PyTorch-based benchmark and ...