SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
Summary: SUREL+ replaces redundant offline walks with reusable node sets, using sparse storage and parallel batched joins for irregular sizes. Modular samplers, features, and encoders retain predictive power, yielding 3–11× speedups over SUREL with comparable or better accuracy. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Haoteng Yin (Purdue University)
- 2. Muhan Zhang (Peking University)
- 3. Jianguo Wang (Purdue University)
- 4. Pan Li (Georgia Institute of Technology)
BibTeX Citation
@article{yin_vldb23,
title = {{SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning}},
author = {Yin, Haoteng and Zhang, Muhan and Wang, Jianguo and Li, Pan},
journal = {PVLDB},
series = {{VLDB} '23},
volume = {16},
number = {11},
pages = {2939--2948},
doi = {10.14778/3611479.3611499},
url = {https://doi.org/10.14778/3611479.3611499},
year = {2023}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,695 | GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs | 2024 | VLDB | 5.7990641e-05 |
| 8,504 | Enabling Window-Based Monotonic Graph Analytics with Reusable Transitional Results for Pattern-Consistent Queries | 2024 | VLDB | 5.4132367e-05 |
| 10,019 | Substructure-aware Log Anomaly Detection | 2025 | VLDB | 5.1757914e-05 |
| 10,420 | SG-Serve: Efficient Model Serving for Subgraph-based Graph Representation Learning | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,409 | TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs | 2022 | VLDB | 0.00010854808 |
| 4,549 | Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning | 2022 | VLDB | 6.6364104e-05 |
Previous
Page 1 / 1
Next