This repository contains the implementation for the paper titled Leveraging Transferable Knowledge Concept Graph Embedding for Cold-Start Cognitive Diagnosis, which was published at SIGIR'2023. [Paper][Presentation Video]

Authors: Weibo Gao, Hao Wang, Qi Liu et al.

Email: [email protected]

Tips: The code and documentation will be completed by April.

Install the Python dependencies:

pip install -r requirements.txt

Install the CUDA version of DGL:

• Download the DGL-Cuda package from here.
• Install the DGL-Cuda package (e.g., dgl-1.1.2+cu118-cp311-cp311-win_amd64.whl) using pip install dgl-1.1.2+cu118-cp311-cp311-win_amd64.whl.

To train TechCD:

python train.py

• RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems (SIGIR'2021). [Paper][Code][Presentation Video]
• Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives (AAAI'2024). [Paper][Code]

Please cite this paper if you use our codes. Thanks!

@inproceedings{gao2023leveraging,
  title={Leveraging transferable knowledge concept graph embedding for cold-start cognitive diagnosis},
  author={Gao, Weibo and Wang, Hao and Liu, Qi and Wang, Fei and Lin, Xin and Yue, Linan and Zhang, Zheng and Lv, Rui and Wang, Shijin},
  booktitle={Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={983--992},
  year={2023}
}

• March 16, 2024: Updated codes
• March 14, 2024: Added codes and data examples
• August 29, 2023: Created this project