Graph neural networks (GNNs) have been proven to be effective in various network-related
tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which …

Abstract Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention
in recent years and achieved outstanding performance in many tasks. The success of the …

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

Deception is rapidly growing as an important tool for cyber defence, complementing existing
perimeter security measures to rapidly detect breaches and data theft. One of the factors …

Job mobility prediction is an emerging research topic that can benefit both organizations and
talents in various ways, such as job recommendation, talent recruitment, and career …

Dealing with relational data always required significant computational resources, domain
expertise and task-dependent feature engineering to incorporate structural information into a …

The prosperous development of social e-commerce has spawned diverse recommendation
demands, and accompanied a new recommendation paradigm, share recommendation …

Graph mining tasks often suffer from the lack of supervision from labeled information due to
the intrinsic sparseness of graphs and the high cost of manual annotation. To alleviate this …

Graph auto-encoder is considered a framework for unsupervised learning on graph-
structured data by representing graphs in a low dimensional space. It has been proved very …

Most attempts on extending Graph Neural Networks (GNNs) to Heterogeneous Information
Networks (HINs) implicitly take the direct assumption that the multiple homogeneous …