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.
@article{arxiv.2202.09177,
title = {Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network},
author = {Tianyu Zhao and Cheng Yang and Yibo Li and Quan Gan and Zhenyi Wang and Fengqi Liang and Huan Zhao and Yingxia Shao and Xiao Wang and Chuan Shi},
journal= {arXiv preprint arXiv:2202.09177},
year = {2022}
}