English

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

Machine Learning 2022-01-03 v1 Social and Information Networks

Abstract

Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs across various scenarios. To facilitate robust and reproducible HGNN research, we construct the Heterogeneous Graph Benchmark (HGB), consisting of 11 diverse datasets with three tasks. HGB standardizes the process of heterogeneous graph data splits, feature processing, and performance evaluation. Finally, we introduce a simple but very strong baseline Simple-HGN--which significantly outperforms all previous models on HGB--to accelerate the advancement of HGNNs in the future.

Keywords

Cite

@article{arxiv.2112.14936,
  title  = {Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks},
  author = {Qingsong Lv and Ming Ding and Qiang Liu and Yuxiang Chen and Wenzheng Feng and Siming He and Chang Zhou and Jianguo Jiang and Yuxiao Dong and Jie Tang},
  journal= {arXiv preprint arXiv:2112.14936},
  year   = {2022}
}

Comments

KDD 2021 research track

R2 v1 2026-06-24T08:35:34.954Z