Recent augmentation-based methods showed that message-passing (MP) neural networks often perform poorly on low-degree nodes, leading to degree biases due to a lack of messages reaching low-degree ...
Abstract: Dynamic graph data can not only reveal the rules of network evolution, but also contain a large amount of personal privacy information. The degree of nodes is an important indicator to ...
Abstract: Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed ...
This repository is the implementation of the following paper: Theoretical Insights into Line Graph Transformation on Graph Learning. This project is built on the BREC dataset which includes 400 pairs ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback