HYDRA: Large-scale Social Identity Linkage via Heterogeneous Behavior Modeling
Summary: HYDRA links identities across platforms via heterogeneous-behavior modeling, a structural-consistency graph on core networks, and joint optimization of supervised linkage with cross-platform coherence. Scale: 10M users, 7 networks; gains >=20% over SOTA, up to 4x in settings. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Siyuan Liu
- 2. Shuhui Wang
- 3. Feida Zhu
- 4. Jinbo Zhang
- 5. Ramayya Krishnan
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,784 | Authenticated Online Data Integration Services | 2015 | SIGMOD | 4.6517065e-05 |
| 11,596 | SLIM: Scalable Linkage of Mobility Data | 2020 | SIGMOD | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 370 | Online Search of Overlapping Communities | 2013 | SIGMOD | 0.00025415479 |
| 1,345 | Entity Matching: How Similar Is Similar | 2011 | VLDB | 0.00012468408 |
| 3,510 | Inter-Media Hashing for Large-scale Retrieval from Heterogeneous Data Sources | 2013 | SIGMOD | 7.0258619e-05 |
| 3,992 | Discovering Linkage Points over Web Data | 2013 | VLDB | 6.5544834e-05 |
Previous
Page 1 / 1
Next