ZeroEA: A Zero-Training Entity Alignment Framework via Pre-Trained Language Model
Summary: ZeroEA: a zero-training entity alignment framework that leverages PLMs by converting KG topology into textual prompts via Graph2Prompt and pruning noisy neighbors with a motif-based filter. Outperforms SOTA on 5 benchmarks without training or labeled data. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Nan Huo
- 2. Reynold Cheng
- 3. Ben Kao
- 4. Wentao Ning
- 5. Nur Al Hasan Haldar
- 6. Xiaodong Li
- 7. Jinyang Li
- 8. Mohammad Matin Najafi
- 9. Tian Li
- 10. Ge Qu
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
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 |
|---|---|---|---|---|
| 1,844 | Effective Community Search over Large Spatial Graphs | 2017 | VLDB | 0.00010341077 |
| 3,915 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB | 6.6332294e-05 |
| 4,355 | LargeEA: Aligning Entities for Large-scale Knowledge Graphs | 2022 | VLDB | 6.259483e-05 |
| 11,140 | MOSER: Scalable Network Motif Discovery using Serial Test | 2024 | VLDB | 4.1945683e-05 |
| 11,492 | On Analyzing Graphs with Motif-Paths | 2021 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next