Existing Graph Neural Networks (GNNs) compute the message exchange between nodes
by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by …

Graph convolution networks (GCN) are increasingly popular in many applications, yet
remain notoriously hard to train over large graph datasets. They need to compute node …

Most state-of-the-art Graph Neural Networks focus on node features in the learning process
but ignore edge features. However, edge features also contain essential information in real …

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard
plights in training deep architectures such as vanishing gradients and overfitting, it also …

Graph neural networks (GNNs) learn the representation of graph-structured data, and their
expressiveness can be further enhanced by inferring node relations for propagation …

Graph Convolutional Networks (GCNs) have proved to be a most powerful architecture in
aggregating local neighborhood information for individual graph nodes. Low-rank …

Graphs have been widely adopted to denote structural connections between entities. The
relations are in many cases heterogeneous, but entangled together and denoted merely as …

Graph neural networks (GNNs) aim to learn well-trained representations in a lower-
dimension space for downstream tasks while preserving the topological structures. In recent …

Graph neural networks (GNNs) have demonstrated great success in graph processing.
However, current message-passing-based GNNs have limitations in terms of feature …

Graph neural networks are emerging as continuation of deep learning success wrt graph
data. Tens of different graph neural network variants have been proposed, most following a …