IEEE

Self-Attention Graph Convolution Imputation Network for Spatio-Temporal Traffic Data

Abstract: Missing data in time series is a pervasive problem that serves as obstacles for subsequent traffic data analysis. Consequently, extensive research works have been conducted on traffic ...
IEEE

From Cluster Assumption to Graph Convolution: Graph-Based Semi-Supervised Learning Revisited

Abstract: Graph-based semi-supervised learning (GSSL) has long been a research focus. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional ...
Frontiers

Association prediction of lncRNAs and diseases using multiview graph convolution neural network

Long noncoding RNAs (lncRNAs) regulate physiological processes via interactions with macromolecules such as miRNAs, proteins, and genes, forming disease-associated regulatory networks. However, ...
GitHub

Hierarchical Convolution and Graph Net for Utilizing Structural Information of Image

Create a folder named 'ckpt' in './viz_nodes' and download the checkpoints of GraphConvNet-Ti or GraphConvNet-S and put them in './viz_nodes/ckpt' Open viz_demo.ipnb, and set arguments (arch, etc.) ...
GitHub

Duntem/Wind-Power-Forecasting-Using-Multi-level-Adaptive-Graph-Convolution-Neural-Network-

The overall structure of the codes refers to the official baseline. The submit.zip here is our final submission file. Wind power is a rapidly growing source of clean energy. Accurate wind power ...
Purdue University

Convolution integral: response to step

In a lecture example, we used the convolution integral approach to study the response of an undamped oscillator excited by the rectangular pulse shown below. Here we will apply the graphical ...