The paper presents graph attention networks (GATs), which it describes as novel neural network architectures for graph-structured data that use masked self-attentional layers to address shortcomings of prior graph-convolution methods.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Graph Attention Networks → states its contribution → The paper presents graph attention networks (GATs), which it describes as novel neural network architectures for graph-structured data that use masked self-attentional layers to address shortcomings of prior graph-convolution methods.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.