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 (University of Hong Kong)
- 2. Reynold Cheng (University of Hong Kong)
- 3. Ben Kao (University of Hong Kong)
- 4. Wentao Ning (University of Hong Kong)
- 5. Nur Al Hasan Haldar (University of Western Australia)
- 6. Xiaodong Li (University of Hong Kong)
- 7. Jinyang Li (University of Hong Kong)
- 8. Mohammad Matin Najafi (University of Hong Kong)
- 9. Tian Li (TCL Research)
- 10. Ge Qu (University of Hong Kong)
BibTeX Citation
@article{huo_vldb24,
title = {{ZeroEA: A Zero-Training Entity Alignment Framework via Pre-Trained Language Model}},
author = {Huo, Nan and Cheng, Reynold and Kao, Ben and Ning, Wentao and Haldar, Nur Al Hasan and Li, Xiaodong and Li, Jinyang and Najafi, Mohammad Matin and Li, Tian and Qu, Ge},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {7},
pages = {1765--1774},
doi = {10.14778/3654621.3654640},
url = {https://doi.org/10.14778/3654621.3654640},
year = {2024}
}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 |
|---|---|---|---|---|
| 1,378 | Effective Community Search over Large Spatial Graphs | 2017 | VLDB | 0.00010971508 |
| 4,056 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB | 6.9344762e-05 |
| 4,402 | LargeEA: Aligning Entities for Large-scale Knowledge Graphs | 2022 | VLDB | 6.7232199e-05 |
| 11,346 | MOSER: Scalable Network Motif Discovery using Serial Test | 2024 | VLDB | 5.093636e-05 |
| 11,690 | On Analyzing Graphs with Motif-Paths | 2021 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,374 | GeoKGM: A Multimodal Large Language Model for Zero-Shot Knowledge Graph Completion in Geospatial Databases | 2026 | SIGMOD |
| 2 | 7,134 | PromptEM: Prompt-tuning for Low-resource Generalized Entity Matching | 2023 | VLDB |
| 3 | 10,318 | In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration | 2026 | SIGMOD |
| 4 | 2,463 | A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching | 2020 | SIGMOD |
| 5 | 10,248 | Generalized Entity Matching with Adaptivity via Large Language Models | 2026 | SIGMOD |
| 6 | 8,441 | A Critical Re-evaluation of Neural Methods for Entity Alignment | 2022 | VLDB |
| 7 | 2,290 | ZeroER: Entity Resolution using Zero Labeled Examples | 2020 | SIGMOD |
| 8 | 9,063 | Deep Active Alignment of Knowledge Graph Entities and Schemata | 2023 | SIGMOD |
| 9 | 4,056 | A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs | 2020 | VLDB |
| 10 | 4,402 | LargeEA: Aligning Entities for Large-scale Knowledge Graphs | 2022 | VLDB |