Graph neural networks (GNNs) rely heavily on architecture design and artificial
hyperparameters, often resulting in expensive manual effort and poor performance …

Graph representation learning has been widely applied to graph tasks such as node
classification, link prediction, graph-level classification and so on. Graph representation …

Graphs are widely used to model various practical applications. In recent years, graph
convolution networks (GCNs) have attracted increasing attention due to the extension of …

Abstract Graph Convolutional Networks (GCNs), aiming to obtain the representation of a
node by aggregating its neighbors, have demonstrated great power in tackling various …

Graph Convolutional Networks (GCNs) have become state-of-the-art methods in many
supervised and semi-supervised graph representation learning scenarios. In order to …

It is common knowledge that using directional antennas is often mandatory for Multi-hop ad-
hoc wireless networks to provide satisfying quality of service, especially when dealing with …

Graph representation learning (GRL) has recently drawn a lot of attention due to its
advantage in solving various machine learning tasks on graphs/networks, ranging from drug …

The challenges posed by the future wireless communication network, which will be a huge
system with more complex structures, diverse functions, and massive communication ends …

In this paper, we propose a model using a graph convolution network for predicting the
accuracy of the automatically generated convolution neural network (CNN). In recent years …

Graphs contain a plethora of valuable information about the underlying data which can be
extracted, analyzed, and visualized using Machine Learning (ML). The challenge is that …