GEEA

This repository is the official implementation of Revisit and Outstrip Entity Alignment: A Perspective of Generative Models, ICLR 2024.

News

• 2024-02 We preprint our Survey Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey [Repo].
• 2024-02 We preprint our Paper ASGEA: Exploiting Logic Rules from Align-Subgraphs for Entity Alignment.

Quick Start

1. Download Datasets

Download datasets from MCLEA and MEAformer.

2. Install Packages

pip install -r requirement.txt

3. Run Script

sh run_geea.sh 0 DBP15K zh-en 0.3 

4. For Other Datasets

sh run_geea.sh 0 DBP15K ja-en 0.3 
sh run_geea.sh 0 DBP15K fr-en 0.3 
sh run_geea.sh 0 FBDB15K norm 0.2
sh run_geea.sh 0 FBYG15K norm 0.2

Special Thanks

This source code is adaped from the official repository of MEAformer.

Citation

@inproceedings{GEEA,
    author = {Lingbing Guo and
              Zhuo Chen and
              Jiaoyan Chen and
              Yin Fang and
              Wen Zhang and
              Huajun Chen},
    title = {Revisit and Outstrip Entity Alignment: {A} Perspective of Generative Models},
    booktitle = {ICLR},
    year = {2024}
}