Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
Summary: Co-design of learning and system for scalable SGRL using walk-based subgraph decomposition to reuse walks and cut extraction redundancy. SUREL scales to millions of nodes/edges, delivering ~10x speed-up over SGRL baselines and up to 50% accuracy gains vs canonical GNNs. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Haoteng Yin (Purdue University)
- 2. Muhan Zhang (Peking University)
- 3. Yanbang Wang (Cornell University)
- 4. Jianguo Wang (Purdue University)
- 5. Pan Li (Purdue University)
BibTeX Citation
@article{yin_vldb22,
title = {{Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning}},
author = {Yin, Haoteng and Zhang, Muhan and Wang, Yanbang and Wang, Jianguo and Li, Pan},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {11},
pages = {2788--2796},
doi = {10.14778/3551793.3551831},
url = {https://doi.org/10.14778/3551793.3551831},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 6 of 6 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 5,677 | SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning | 2023 | VLDB | 6.041013e-05 |
| 6,109 | GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs | 2024 | VLDB | 5.8845577e-05 |
| 10,208 | Substructure-aware Log Anomaly Detection | 2025 | VLDB | 5.0596605e-05 |
| 10,520 | A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness | 2026 | SIGMOD | 4.9793485e-05 |
| 10,609 | SG-Serve: Efficient Model Serving for Subgraph-based Graph Representation Learning | 2026 | SIGMOD | 4.9793485e-05 |
| 11,459 | Towards Ideal Temporal Graph Neural Networks: Evaluations and Conclusions after 10,000 GPU Hours | 2025 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 211 | AliGraph: A Comprehensive Graph Neural Network Platform | 2019 | VLDB | 0.00024816965 |
| 1,033 | AGL: A Scalable System for Industrial-purpose Graph Machine Learning | 2020 | VLDB | 0.00012397734 |
| 2,439 | Accelerating Large Scale Real-Time GNN Inference using Channel Pruning | 2021 | VLDB | 8.4652234e-05 |
| 3,752 | G3: When Graph Neural Networks Meet Parallel Graph Processing Systems on GPUs | 2020 | VLDB | 7.0517024e-05 |
| 3,899 | Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization | 2021 | VLDB | 6.9358695e-05 |
Previous
Page 1 / 1
Next