Abstract: Many studies have achieved excellent performance in analyzing graph-structured data. However, learning graph-level representations for graph classification is still a challenging task.
Abstract: Heterogeneous graphs (HGs) with multiple entity and relation types are common in real-world networks. Heterogeneous graph neural networks (HGNNs) have shown promise for learning HG ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results