Spade: A Real-Time Fraud Detection Framework on Evolving Graphs
Summary: Spade: an incremental framework that maintains dense-subgraph (fraudulent community) detection on million-scale evolving transaction graphs in hundreds of microseconds. Offers batch/edge-group updates and APIs to plug suspiciousness semantics, incrementalizing peeling algorithms for up to 10^6× speedups vs static re-computation. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Jiaxin Jiang
- 2. Yuan Li
- 3. Bingsheng He
- 4. Bryan Hooi
- 5. Jia Chen
- 6. Johan Kok Zhi Kang
Incoming Citations (Sorted by Pagerank)
Showing 10 of 10 citing papers.
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 |
|---|---|---|---|---|
| 57 | Discovering Large Dense Subgraphs in Massive Graphs | 2005 | VLDB | 0.00065491112 |
| 644 | Densest Subgraph in Streaming and MapReduce | 2012 | VLDB | 0.00018748988 |
| 961 | DBSCAN Revisited: Mis-Claim, Un-Fixability, and Approximation | 2015 | SIGMOD | 0.00015001792 |
| 2,049 | Community Detection in Social Networks: An In-depth Benchmarking Study with a Procedure-Oriented Framework | 2015 | VLDB | 9.6894639e-05 |
| 7,158 | GPU-Accelerated Graph Label Propagation for Real-Time Fraud Detection | 2021 | SIGMOD | 4.8143783e-05 |
Previous
Page 1 / 1
Next