Papers › Scalable Graph Neural Networks for Heterogeneous Graphs

Scalable Graph Neural Networks for Heterogeneous Graphs

19 Nov 2020arXiv:2011.09679archive 2025-07-28

Lingfan Yu, Jiajun Shen, Jinyang Li, Adam Lerer

Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks by simply operating on graph-smoothed node features, rather than using end-to-end learned feature hierarchies that are challenging to scale to large graphs. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities. We propose Neighbor Averaging over Relation Subgraphs (NARS), which trains a classifier on neighbor-averaged features for randomly-sampled subgraphs of the "metagraph" of relations. We describe optimizations to allow these sets of node features to be computed in a memory-efficient way, both at training and inference time. NARS achieves a new state of the art accuracy on several benchmark datasets, outperforming more expensive GNN-based methods

PaperPDFConference PDFCode

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

Code

facebookresearch/NARS officialmentioned in papermentioned 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

Heterogeneous Node ClassificationNode Property Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) NARS Macro-F1 93.36 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification ACM (Heterogeneous Node Classification) NARS Micro-F1 93.31 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) NARS Macro-F1 94.18 #3 of 11 Archive leaderboard report
Heterogeneous Node Classification DBLP (Heterogeneous Node Classification) NARS Micro-F1 94.61 #3 of 11 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) NARS Macro-F1 49.98 #2 of 9 Archive leaderboard report
Heterogeneous Node Classification Freebase (Heterogeneous Node Classification) NARS Micro-F1 63.26 #2 of 9 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) NARS Macro-F1 63.51 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification IMDB (Heterogeneous Node Classification) NARS Micro-F1 66.18 #4 of 11 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field NARS MRR 85.15 #2 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-L1-Field NARS NDCG 86.06 #2 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue NARS MRR 34.38 #2 of 5 Archive leaderboard report
Heterogeneous Node Classification OAG-Venue NARS NDCG 52.28 #2 of 5 Archive leaderboard report
Node Property Prediction ogbn-mag NARS Ext. data No #22 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS Number of params 4130149 #22 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS Test Accuracy 0.5240 ± 0.0016 #22 of 39 Archive leaderboard report
Node Property Prediction ogbn-mag NARS Validation Accuracy 0.5372 ± 0.0009 #22 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.

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