Graph Kernel Attention Transformers: Toward Expressive and Scalable Graph Processing | Synced
A research team from Google Brain, Columbia University and University of Oxford proposes Graph Kernel Attention Transformers (GKATs), a new class of graph neural network that achieves greater expre...
Source: Synced | AI Technology & Industry Review
A research team from Google Brain, Columbia University and University of Oxford proposes Graph Kernel Attention Transformers (GKATs), a new class of graph neural network that achieves greater expressive power than SOTA GNNs while reducing computation burdens.