Abstract: We investigate graph convolution networks with efficient learning from higher-order graph convolutions and direct learning from adjacency matrices for node classification. We revisit the ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback