GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs

TL;DR

GripNet introduces a novel supergraph-based framework for scalable and semantically-aware heterogeneous graph representation learning, improving performance in various downstream tasks.

Contribution

It proposes a new supergraph data structure and a flexible propagation network that effectively captures semantic relationships and scales to large graphs.

Findings

Outperforms existing methods in link prediction

Achieves higher accuracy in node classification

Demonstrates scalability on large-scale graphs

Abstract

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.