EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges

Xu Cheng, Liang Yao, Feng He, Yukuo Cen, Yufei He, Wenzheng Feng, Chenhui Zhang, Hongyun Cai, Jie Tang

ACM Transactions on Knowledge Discovery from Data · 30.06.2026 · 20 (5) · 1-24

DOI: 10.1145/3801100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 20.05.2026. Verfasst von Xu Cheng und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of China, New Cornerstone Science Foundation through the XPLORER PRIZE.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Networks (GNNs) have emerged as powerful tools for various graph mining tasks, yet existing scalable solutions often struggle to balance execution efficiency with prediction accuracy. These difficulties stem from iterative message-passing techniques, which place significant computational demands and require extensive Graphics Processing Unit (GPU) memory, particularly when dealing with the neighbor explosion issue inherent in large-scale graphs. This article introduces a scalable, low-cost, flexible, and efficient GNN framework called LPS-GNN, which can perform representation learning on 100billion-edge graph with a single GPU in 10 hours and shows a 13.8% improvement in User Acquisition scenarios. We examine existing graph partitioning methods and design a superior graph partition algorithm named Label Propagation with METIS (LPMetis). In particular, LPMetis outperforms current state-of-the-art (SOTA) approaches on various evaluation metrics. In addition, our article proposes a subgraph augmentation strategy to enhance the model’s predictive performance. It exhibits excellent compatibility, allowing the entire framework to accommodate various GNN algorithms. Successfully deployed on the Tencent platform, LPS-GNN has been tested on public and real-world datasets, achieving performance lifts of 8.24% to 13.89% over SOTA models in online applications.

Förderung

  • Natural Science Foundation of China
  • New Cornerstone Science Foundation through the XPLORER PRIZE

Zitieren

APA

Cheng, X., Yao, L., He, F., Cen, Y., He, Y., Feng, W., Zhang, C., Cai, H., & Tang, J. (2026). LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges. ACM Transactions on Knowledge Discovery from Data, 20(5), 1-24. https://doi.org/10.1145/3801100

Vancouver

Cheng X, Yao L, He F, Cen Y, He Y, Feng W, et al. LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges. ACM Transactions on Knowledge Discovery from Data. 2026;20(5):1-24. doi:10.1145/3801100

BibTeX
@article{Cheng2026,
  author = {Cheng, Xu and Yao, Liang and He, Feng and Cen, Yukuo and He, Yufei and Feng, Wenzheng and Zhang, Chenhui and Cai, Hongyun and Tang, Jie},
  title = {LPS-GNN: Deploying Graph Neural Networks on Graphs with 100-Billion Edges},
  journal = {ACM Transactions on Knowledge Discovery from Data},
  year = {2026},
  volume = {20},
  number = {5},
  pages = {1--24},
  doi = {10.1145/3801100}
}
Kostenlos starten →