Papers › Simple and Efficient Heterogeneous Graph Neural Network

Simple and Efficient Heterogeneous Graph Neural Network

6 Jul 2022arXiv:2207.02547archive 2025-07-28

Xiaocheng Yang, Mingyu Yan, Shirui Pan, Xiaochun Ye, Dongrui Fan

Heterogeneous graph neural networks (HGNNs) have powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations. Existing HGNNs inherit many mechanisms from graph neural networks (GNNs) over homogeneous graphs, especially the attention mechanism and the multi-layer structure. These mechanisms bring excessive complexity, but seldom work studies whether they are really effective on heterogeneous graphs. This paper conducts an in-depth and detailed study of these mechanisms and proposes Simple and Efficient Heterogeneous Graph Neural Network (SeHGNN). To easily capture structural information, SeHGNN pre-computes the neighbor aggregation using a light-weight mean aggregator, which reduces complexity by removing overused neighbor attention and avoiding repeated neighbor aggregation in every training epoch. To better utilize semantic information, SeHGNN adopts the single-layer structure with long metapaths to extend the receptive field, as well as a transformer-based semantic fusion module to fuse features from different metapaths. As a result, SeHGNN exhibits the characteristics of simple network structure, high prediction accuracy, and fast training speed. Extensive experiments on five real-world heterogeneous graphs demonstrate the superiority of SeHGNN over the state-of-the-arts on both accuracy and training speed.

PaperPDFCode

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

Code

ict-gimlab/sehgnn officialmentioned in papermentioned on GitHubpytorch report
ICT-GIMLab/SeHGNN 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

Graph Neural NetworkHeterogeneous Node ClassificationNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) SeHGNN Claim Classification Macro-F1 93.95 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) SeHGNN Micro-F1 93.87 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) SeHGNN Macro-F1 94.86 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) SeHGNN Micro-F1 95.24 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) SeHGNN Macro-F1 50.71 #8 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) SeHGNN Micro-F1 63.41 #8 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) SeHGNN Macro-F1 66.63 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) SeHGNN Micro-F1 68.21 #10 of 11 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field SeHGNN MRR 84.95 #3 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field SeHGNN NDCG 86.01 #3 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue SeHGNN MRR 29.11 #5 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue SeHGNN NDCG 46.75 #5 of 5 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN (ComplEx embs) Ext. data No #10 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN (ComplEx embs) Number of params 8371231 #10 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN (ComplEx embs) Test Accuracy 0.5719 ± 0.0012 #10 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN (ComplEx embs) Validation Accuracy 0.5917 ± 0.0009 #10 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN Ext. data No #11 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN Number of params 8371231 #11 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN Test Accuracy 0.5671 ± 0.0014 #11 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag SeHGNN Validation Accuracy 0.5870 ± 0.0008 #11 of 39 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

Graph Neural Network

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