Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data. It operates feature the structure, through aggregating features of neighbor nodes to obtain embedding each target node. Owing strong representation power, recent research shows GCN achieves state-of-the-art performance several tasks such as recommendation linked document classification...

Researchers have recently proposed plenty of heterogeneous graph neural networks (HGNNs) due to the ubiquity graphs in both academic and industrial areas. Instead pursuing a more powerful HGNN model, this paper, we are interested devising versatile plug-and-play module, which accounts for distilling relational knowledge from pre-trained HGNNs. To best our knowledge, first propose HI gh-order RE...

Graph representation learning is a significant challenge in graph signal processing (GSP). The flourishing development of neural networks (GNNs) provides effective representations for GSP. To effectively learn from signals, we propose regularized network based on approximate fractional order gradients (FGNN). propagates the information between neighboring nodes. approximation strategy calculati...

The emph{Harary index} $H(G)$ of a connected graph $G$ is defined as $H(G)=sum_{u,vin V(G)}frac{1}{d_G(u,v)}$ where $d_G(u,v)$ is the distance between vertices $u$ and $v$ of $G$. The Steiner distance in a graph, introduced by Chartrand et al. in 1989, is a natural generalization of the concept of classical graph distance. For a connected graph $G$ of order at least $2$ ...