GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
This work addresses scalability and integration issues in heterogeneous graph learning, which is important for applications like recommendation systems and knowledge graphs, but it appears incremental as it builds on existing graph neural network methods.
The paper tackles the problem of heterogeneous graph representation learning by proposing GripNet, a framework that uses a supergraph structure to propagate information, achieving superior performance in link prediction, node classification, and data integration tasks.
Heterogeneous graph representation learning aims to learn low-dimensional vector representations of different types of entities and relations to empower downstream tasks. Existing methods either capture semantic relationships but indirectly leverage node/edge attributes in a complex way, or leverage node/edge attributes directly without taking semantic relationships into account. When involving multiple convolution operations, they also have poor scalability. To overcome these limitations, this paper proposes a flexible and efficient Graph information propagation Network (GripNet) framework. Specifically, we introduce a new supergraph data structure consisting of supervertices and superedges. A supervertex is a semantically-coherent subgraph. A superedge defines an information propagation path between two supervertices. GripNet learns new representations for the supervertex of interest by propagating information along the defined path using multiple layers. We construct multiple large-scale graphs and evaluate GripNet against competing methods to show its superiority in link prediction, node classification, and data integration.