GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
arXiv:2010.15914 · doi:10.1016/j.patcog.2022.108973
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Distributed Representations of Words and Phrases and their Compositionality
- Neural Message Passing for Quantum Chemistry
- Modeling polypharmacy side effects with graph convolutional networks
- Fast Graph Representation Learning with PyTorch Geometric
- Variational Graph Auto-Encoders
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
- Deep Recurrent Quantization for Generating Sequential Binary Codes
- Graph Transformer Networks
- KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features
- Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
- Cross-domain Network Representations