Since real-world objects and their interactions are often multi-modal and multi-typed,
heterogeneous networks have been widely used as a more powerful, realistic, and generic …

Graph Neural Networks (GNNs) have been widely used for the representation learning of
various structured graph data, typically through message passing among nodes by …

Graph neural networks (GNNs) have achieved superior performance in various applications,
but training dedicated GNNs can be costly for large-scale graphs. Some recent work started …

Graph neural networks (GNNs) have been widely used in deep learning on graphs. They
can learn effective node representations that achieve superior performances in graph …

Understanding the interconnected relationships of large-scale information networks like
social, scholar and Internet of Things networks is vital for tasks like recommendation and …

Graph embedding has been intensively studied recently, due to the advance of various
neural network models. Theoretical analyses and empirical studies have pushed forward the …

In this paper, we propose a novel framework to automatically utilize task-dependent
semantic information which is encoded in heterogeneous information networks (HINs) …

We introduce submodular hypergraphs, a family of hypergraphs that have different
submodular weights associated with different cuts of hyperedges. Submodular hypergraphs …

Graph convolutional networks (GCNs) are a powerful class of graph neural networks.
Trained in a semi-supervised end-to-end fashion, GCNs can learn to integrate node features …

The automated construction of topic taxonomies can benefit numerous applications,
including web search, recommendation, and knowledge discovery. One of the major …