https://github.com/HKUST-KnowComp/WFRE

Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport (Findings-ACL 2023)
https://github.com/HKUST-KnowComp/WFRE

Last synced: about 1 month ago
JSON representation

Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport (Findings-ACL 2023)

• Host: GitHub
• URL: https://github.com/HKUST-KnowComp/WFRE
• Owner: HKUST-KnowComp
• Created: 2023-05-02T16:12:46.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-05-04T10:18:17.000Z (over 1 year ago)
• Last Synced: 2024-08-02T19:37:42.097Z (5 months ago)
• Language: Python
• Homepage:
• Size: 82 KB
• Stars: 11
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-logical-query - WFRE

README

        
# Wasseretein-Fisher-Rao Embedding

The implementation for ACL 2023 findings paper:

> Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport

by Zihao Wang, Weizhi Fei, Hang Yin, Yangqiu Song, Ginny Y. Wong, and Simon See.

# Prepare the data

The KG data (FB15k, FB15k-237, NELL995) should be put into under 'data/' folder. We use the [data](http://snap.stanford.edu/betae/KG_data.zip) provided in the [KGReasoning](https://github.com/snap-stanford/KGReasoning).

The structure of the data folder should be at least and we follow the query type of EFO-1 and transfer the data.

```

data

	|---FB15k-237-betae

	|---FB15k-betae

	|---NELL-betae

```

The OpsTree is generated by `binary_formula_iterator` in `fol/foq_v2.py`. The overall process is managed in `formula_generation.py`. Transform beta queries to EFO-1 is the next step.

To generate the formula and transform the queries data, just run

```bash

python formula_generation.py

python transform_beta_data.py

```

# Run experiments on different knowledge graphs

The hyperparameters in three datasets is provided in config/papers.

To get our results in paper just run

```bash

python main.py -config config/papers/NELL.yaml

```