Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
This work addresses the reproducibility and evaluation bottlenecks for researchers in heterogeneous graph neural networks, though it is incremental as it builds on existing HGNN frameworks.
The authors tackled the challenge of evaluating and comparing heterogeneous graph neural networks (HGNNs) by proposing Space4HGNN, a modular platform that standardizes implementations and analysis, leading to distilled design insights validated through experiments.
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.