35 papers with code • 8 benchmarks • 6 datasets
The regression task is similar to graph classification but using different loss function and performance metric.
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.
Ranked #1 on Graph Classification on IPC-grounded
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.
Ranked #2 on Node Classification on Wiki-Vote
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.
Ranked #2 on Node Classification on Flickr
We show that the expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.
Ranked #1 on Knowledge Graphs on WikiKG90M-LSC
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
Ranked #2 on Graph Regression on Lipophilicity