SAINT+ Paper Implementaions for Riiid! Answer Correctness Prediction Competition from Kaggle.
This paper added an additional features to existing architecture, SAINT: Separated Self-Attentive Neural Knowledge Tracing.
SAINT: Separated Self-Attentive Neural Knowledge Tracing is from this paper Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing, its pytorch implementation is here for the same dataset given above.
- Change config.py- Datafile location, device, batch size.
- Saint.py file code is used while training in train.py directly.
- finally, run the train.py file in command line.
@misc{shin2020saint,
title={SAINT+: Integrating Temporal Features for EdNet Correctness Prediction},
author={Dongmin Shin and Yugeun Shim and Hangyeol Yu and Seewoo Lee and Byungsoo Kim and Youngduck Choi},
year={2020},
eprint={2010.12042},
archivePrefix={arXiv},
primaryClass={cs.CY}
}
@misc{choi2020appropriate,
title={Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing},
author={Youngduck Choi and Youngnam Lee and Junghyun Cho and Jineon Baek and Byungsoo Kim and Yeongmin Cha and Dongmin Shin and Chan Bae and Jaewe Heo},
year={2020},
eprint={2002.07033},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent