Data

Tools

Indexes

Applications

Experiments

Open Source Science

cafe

Knowledge Graph Completion using Neighborhood-Aware Features (published in EAAI)

https://github.com/deal-us/cafe

Science Score: 49.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 5 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: sciencedirect.com, zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation

Repository

Knowledge Graph Completion using Neighborhood-Aware Features (published in EAAI)

Basic Info
  • Host: GitHub
  • Owner: DEAL-US
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 15.6 MB
Statistics
  • Stars: 6
  • Watchers: 0
  • Forks: 4
  • Open Issues: 2
  • Releases: 0
Created almost 7 years ago · Last pushed almost 3 years ago
Metadata Files
Readme Citation

README.md

CAFE: Knowledge Graph Completion using Neighborhood-Aware Features DOI:10.1016/j.engappai.2021.104302

Source code for the CAFE tool, which evaluates triples for KG Completion.

This repository contains the necessary code to generate feature vectors using our proposed context-aware features, as well as the datasets that we used in our paper. To run CAFE, install the dependencies listed in requirements.txt and run python main.py <dataset> <max-ctx>, where <dataset> is the name of the dataset to use (which should be in the datasets/ folder) and <max-ctx> is the maximum path length used to generate neighborhood subgraphs.

If you find CAFE useful, please consider citing it as:

bibtex @article{borrego2021CAFE, author = {Borrego, Agust{\'i}n and Ayala, Daniel and Hern{\'a}ndez, Inma and Rivero, Carlos R. and Ruiz, David}, title = {{CAFE}: Knowledge graph completion using neighborhood-aware features}, journal = {Engineering Applications of Artificial Intelligence}, volume = {103}, pages = {104302}, year = {2021}, issn = {0952-1976}, doi = {10.1016/j.engappai.2021.104302}, url = {https://www.sciencedirect.com/science/article/pii/S0952197621001500} }

Owner

  • Name: Data Engineering Applications Lab
  • Login: DEAL-US
  • Kind: organization
  • Location: Seville, Spain

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • Keras ==2.3.1
  • decorator ==4.4.0
  • networkx ==2.3
  • numpy ==1.19.4
  • scipy ==1.4.1
  • tensorflow ==2.5.2
  • tqdm ==4.32.1