Welcome to the official repository of KHG-Aclair, a research project focused on enhancing attention mechanisms using Knowledge HyperGraphs and Contrastive Learning.
KHG-Aclair aims to improve attention mechanisms in machine learning models by leveraging Knowledge HyperGraphs (KHGs). This repository contains the source code and datasets used in the research paper titled "KHG-Aclair". Please note that the code is currently being organized and will soon be made available in a well-structured format.
- Will Be:
- Update:
- Soon:
As of now, the repository is undergoing organization and cleanup. The well-structured code and datasets will be published soon.
The dataset is available via the following link due to file size issues. Dataset Download Link
If you use KHG-Aclair in your research or find it helpful, please consider citing our paper.
@article{yourcitationdetails, title={KHG-Aclair: Knowledge HyperGraph-based Attention with Contrastive Learning}, author={Hyejin Park, Taeyoon Lee, Kyungwon Kim}, journal={Will be submitted to the International Journal}, year={2024}, }
This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the government of Korea (MSIT) under grant number 2021-0-01352, titled "Development of technology for validating the autonomous driving services in perspective of laws and regulations.
This project was developed with reference to the source codes from KGCL and HyperGAT. We express our deep gratitude for their contributions and ideas.
For questions or inquiries, please contact Hyejin Park or Taeyoon Lee.