Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
arXiv:2202.09177 · doi:10.1145/3477495.3531720
Abstract
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform Space4HGNN by defining a design space for HGNNs based on the unified framework, which offers modularized components, reproducible implementations, and standardized evaluation for HGNNs. Finally, we conduct experiments to analyze the effect of different designs. With the insights found, we distill a condensed design space and verify its effectiveness.
SIGIR2022
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Graph Transformer Networks
- Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources
- Heterogeneous Graph Collaborative Filtering
- KGTuner: Efficient Hyper-parameter Search for Knowledge Graph Learning