PyKT

PyKT is a python library build upon PyTorch to train deep learning based knowledge tracing models. The library consists of a standardized set of integrated data preprocessing procedures on 7 popular datasets across different domains, 5 detailed prediction scenarios, 10 frequently compared DLKT approaches for transparent and extensive experiments.

Installation

Use the following command to install PyKT:

Create conda envirment.

conda create --name=pykt python=3.7.5
source activate pykt

pip install -U pykt-toolkit -i  https://pypi.python.org/simple 

References

Projects

1. https://github.com/hcnoh/knowledge-tracing-collection-pytorch
2. https://github.com/arshadshk/SAKT-pytorch
3. https://github.com/shalini1194/SAKT
4. https://github.com/arshadshk/SAINT-pytorch
5. https://github.com/Shivanandmn/SAINT_plus-Knowledge-Tracing-
6. https://github.com/arghosh/AKT
7. https://github.com/JSLBen/Knowledge-Query-Network-for-Knowledge-Tracing
8. https://github.com/xiaopengguo/ATKT
9. https://github.com/jhljx/GKT

Papers

1. DKT: Deep knowledge tracing
2. DKT+: Addressing two problems in deep knowledge tracing via prediction-consistent regularization
3. DKT-Forget: Augmenting knowledge tracing by considering forgetting behavior
4. KQN: Knowledge query network for knowledge tracing: How knowledge interacts with skills
5. DKVMN: Dynamic key-value memory networks for knowledge tracing
6. ATKT: Enhancing Knowledge Tracing via Adversarial Training
7. GKT: Graph-based knowledge tracing: modeling student proficiency using graph neural network
8. SAKT: A self-attentive model for knowledge tracing
9. SAINT: Towards an appropriate query, key, and value computation for knowledge tracing
10. AKT: Context-aware attentive knowledge tracing