SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
Summary: SUREL+ replaces sampled-walk proxies with node sets to remove node redundancy, using a sparse storage layout and a parallel set-join operator to handle variable-size sets. Modular samplers/encoders recover structural cues; yields 3–11x speedups vs SUREL (~20x vs other SGRL) with comparable or improved accuracy. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Haoteng Yin
- 2. Muhan Zhang
- 3. Jianguo Wang
- 4. Pan Li
Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,750 | GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs | 2024 | VLDB | 4.6565447e-05 |
| 9,486 | Enabling Window-Based Monotonic Graph Analytics with Reusable Transitional Results for Pattern-Consistent Queries | 2024 | VLDB | 4.3300131e-05 |
| 9,871 | Substructure-aware Log Anomaly Detection | 2025 | VLDB | 4.2626861e-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 |
|---|---|---|---|---|
| 1,388 | TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs | 2022 | VLDB | 0.00012249747 |
| 5,007 | Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning | 2022 | VLDB | 5.7581517e-05 |
Previous
Page 1 / 1
Next