code for "EchoEA: Echo Information between Entities and Relations for Entity Alignment"
- PyTorch 1.8.1 + cuda 10.2
- apex (alternative)
- torch-scatter, torch-sparse, torch-cluster, torch-spline-conv, torch-geometric
pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.1+cu102.html
pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.1+cu102.html
pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-1.8.1+cu102.html
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.8.1+cu102.html
pip install torch-geometric
To prepare attribute similarity and value similarity:
python sim_based_on_attr_n_value.py
Complete version:
python train.py
Ablation:
- Basic: train_basic.py
- w/o PAN: train_basic_woPAN.py
- w/o EN: train_basic_woEN.py
- w/o CAN: train_basic_woCAN.py
- ent_ids_1: ids for entities in source KG;
- ent_ids_2: ids for entities in target KG;
- ref_ent_ids: entity links encoded by ids;
- triples_1: relation triples encoded by ids in source KG;
- triples_2: relation triples encoded by ids in target KG;
We cite the datasets and codes of these repos: GCN-Align, RREA, EMGCN, RAGA. Thanks for their great contributions!