Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks
This work addresses reproducibility and benchmarking issues in heterogeneous graph neural network research, providing standardized tools to accelerate future advancements.
The authors systematically reproduced 12 recent heterogeneous graph neural networks (HGNNs) and found that simple homogeneous GNNs like GAT, with proper settings, often match or outperform them, revealing overestimated progress. They introduced the Heterogeneous Graph Benchmark (HGB) with 11 datasets and a strong baseline Simple-HGN that significantly outperforms previous models.
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.