keras-gat
Keras implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)
view repo
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved state-of-the-art results across three established transductive and inductive graph benchmarks: the Cora and Citeseer citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs are entirely unseen during training).
READ FULL TEXT
In this paper, we study the problem of node representation learning with...
read it
Low-dimensional embeddings of nodes in large graphs have proved extremel...
read it
Learning on 3D structures of large biomolecules is emerging as a distinc...
read it
Graph Attention Network (GAT) and GraphSAGE are neural network architect...
read it
Convolutional neural networks (CNNs) have achieved great success on grid...
read it
Recent research efforts have shown the possibility to discover anticance...
read it
Graph classification is a significant problem in many scientific domains...
read it
Keras implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)
Comments
There are no comments yet.