Papers › Are we really making much progress? Revisiting, benchmarking, and refining...

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

30 Dec 2021arXiv:2112.14936archive 2025-07-28

Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, Jie Tang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

thudm/hgb officialmentioned in paperpytorch report
calderkatyal/CPSC483FinalProject mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingHeterogeneous Node Classification

Datasets

Introduced by this paper, per the archive.

ACM (Heterogeneous Node Classification)DBLP (Heterogeneous Node Classification)Freebase (Heterogeneous Node Classification)IMDB (Heterogeneous Node Classification)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) Simple-HGN Macro-F1 93.42 #3 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) Simple-HGN Micro-F1 93.35 #3 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) Simple-HGN Macro-F1 94.01 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) Simple-HGN Micro-F1 94.46 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) Simple-HGN Macro-F1 47.72 #4 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) Simple-HGN Micro-F1 66.29 #4 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) Simple-HGN Macro-F1 63.53 #3 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) Simple-HGN Micro-F1 67.36 #3 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GATGCN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections