GPU-Accelerated Graph Label Propagation for Real-Time Fraud Detection
Summary: GLP is a GPU-based graph label propagation framework that enables real-time fraud detection on TaoBao's large user-interaction graphs. It offers expressive APIs and GPU-centric optimizations that exploit community structure and power-law properties, delivering 8.2x single-GPU speedup over in-house multicore pipelines on billion-scale workloads. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Chang Ye (Singapore Management University)
- 2. Yuchen Li (Singapore Management University)
- 3. Bingsheng He (National University of Singapore)
- 4. Zhao Li (Alibaba)
- 5. Jianling Sun (Zhejiang University)
BibTeX Citation
@inproceedings{ye_sigmod21,
title = {{GPU-Accelerated Graph Label Propagation for Real-Time Fraud Detection}},
author = {Ye, Chang and Li, Yuchen and He, Bingsheng and Li, Zhao and Sun, Jianling},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3452774},
url = {https://dl.acm.org/doi/10.1145/3448016.3452774},
year = {2021}
}Incoming Citations (Sorted by Pagerank)
Showing 10 of 10 citing papers.
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,064 | Incremental Maintenance for Non-Distributive Aggregate Functions | 2002 | VLDB | 9.2383582e-05 |
| 2,580 | Community Detection in Social Networks: An In-depth Benchmarking Study with a Procedure-Oriented Framework | 2015 | VLDB | 8.3887788e-05 |
| 2,607 | GPU-Accelerated Subgraph Enumeration on Partitioned Graphs | 2020 | SIGMOD | 8.3489531e-05 |
| 2,874 | iBFS: Concurrent Breadth-First Search on GPUs | 2016 | SIGMOD | 8.0094569e-05 |
| 4,157 | GPU-based Graph Traversal on Compressed Graphs | 2019 | SIGMOD | 6.8629037e-05 |
| 4,225 | Realtime Top-k Personalized PageRank over Large Graphs on GPUs | 2020 | VLDB | 6.821373e-05 |
| 5,250 | Parallel Personalized PageRank on Dynamic Graphs | 2018 | VLDB | 6.2992176e-05 |
| 7,573 | Accelerating Exact Constrained Shortest Paths on GPUs | 2021 | VLDB | 5.5938767e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,223 | Everest: GPU-Accelerated System For Mining Temporal Motifs | 2024 | VLDB |
| 2 | 920 | APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding | 2021 | SIGMOD |
| 3 | 7,418 | Distributed Hop-Constrained s-t Simple Path Enumeration at Billion Scale | 2022 | VLDB |
| 4 | 11,465 | MINT: Detecting Fraudulent Behaviors from Time-series Relational Data | 2023 | VLDB |
| 5 | 9,189 | RUSH: Real-time Burst Subgraph Detection in Dynamic Graphs | 2024 | VLDB |
| 6 | 10,758 | Dupin: A Parallel Framework for Densest Subgraph Discovery in Fraud Detection on Massive Graphs | 2025 | SIGMOD |
| 7 | 927 | Real-time Constrained Cycle Detection in Large Dynamic Graphs | 2018 | VLDB |
| 8 | 8,390 | Spade: A Real-Time Fraud Detection Framework on Evolving Graphs | 2023 | VLDB |
| 9 | 4,666 | xFraud: Explainable Fraud Transaction Detection | 2022 | VLDB |
| 10 | 4,171 | Accelerating Dynamic Graph Analytics on GPUs | 2018 | VLDB |