DKT改进模型及论文名称
DKT改进模型及论文名称
- 一、结构图
- 二、模型出处论文
-
- 可解释性问题改进
-
- A-DKT：
- DKVMN
- DKVMN-CA（concept-aware DKVMN）
- EERNN（exercise-enhanced RNN）
- EKT（exercise-aware KT）
- KQN（knowledge query network）
- Deep-IRT（deep item response theory）
- 长期依赖问题改进
-
- LRP（layer-wise relevance propagation）
- Hop-LSTM
- NKT（neural KT）
- SAKT（self attention KT）
- SAINT（separated self-attention neural KT）
- DKT + Transformer
- 缺少学习特征改进
-
- DKT-FE（DKT with feature engineering）
- DKT-DT（DKT with decision trees）
- DKVMN-DT（DKVMN with decision trees）
- DKT + forgetting
- AKT（adaptable KT）
- EHFKT （exercise hierarchical feature enhanced KT）
- LSTMCQ （ LSTM based contextualized Q-matrix）
- DKT-DSC （ DKT with dynamic student classification）/DSCMN（dynamic student classification on memory networks）
- Colearn
- PDKT-C (prerequisite-driven DKT with constraint modeling）
- DKT-S（DKT with side information）
- DHKT（deep hierarchical KT）
- qDKT（question-centric DKT）
- GKT（graph based KT）
- CKT（convolutional KT）
- SKVMN （sequential key-value memory networks）
- DeepFM（deep factorization machines）
- KTM-DLF（knowledge tracing machine by modeling cognitive item difficulty and learning and forgetting）
- DynEMb
- BDKT （Bayesian neural network DKT）
- Q-Embedding
一、结构图
二、模型出处论文
可解释性问题改进
注意力机制
A-DKT：
Liu Dong, Dai Huanhuan, Zhang Yunping, et al. Deep knowledge tracking based on attention mechanism for student performance prediction
https://ieeexplore.ieee.org/document/9142472
https://sci-hub.st/10.1109/CSEI50228.2020.9142472
DKVMN
Zhang Jiani, Shi Xingjian, King I, et al. Dynamic key-value memory networks for knowledge tracing
http://papers.www2017.com.au.s3-website-ap-southeast-2.amazonaws.com/proceedings/p765.pdf
DKVMN-CA（concept-aware DKVMN）
Ai Fangzhe, Chen Yishuai, Guo Yuchun, et al. Concept-aware deep knowledge tracing and exercise recommendation in an online learning system
EERNN（exercise-enhanced RNN）
Su Yu, Liu Qingwen, Liu Qi, et al. Exercise-enhanced sequential modeling for student performance prediction
http://dm.ustc.edu.cn/paper_pdf/2018/Yu-Su-AAAI.pdf
EKT（exercise-aware KT）
Huang Zhenya, Yin Yu, Chen Enhong, et al. EKT: Exercise-aware knowledge tracing for student performance prediction
http://bigdata.ustc.edu.cn/paper_pdf/2019/Qi-Liu-TKDE.pdf
自解释模型
KQN（knowledge query network）
Lee J, Yeung D Y. Knowledge query network for knowledge tracing: How knowledge interacts with skills
Deep-IRT（deep item response theory）
Yeung C K. Deep-IRT: Make deep learning-based knowledge tracing explainable using item response theory
长期依赖问题改进
LRP（layer-wise relevance propagation）
Lu Yu, Wang Deliang, Meng Qinggang, et al. Towards interpretable deep learning models for knowledge tracing
Hop-LSTM
Abdelrahman G, Wang Qing. Knowledge tracing with sequential key-value memory networks
NKT（neural KT）
Sha Long, Hong Pengyu. Neural knowledge tracing
SAKT（self attention KT）
Pandey S, Karypis G. A Self-attentive model for knowledge tracing
SAINT（separated self-attention neural KT）
Choi Y, Lee Y, Cho J, et al. Towards an appropriate query, key, and value computation for knowledge tracing
DKT + Transformer
Pu Shi, Yudelson M, Ou Lu, et al. Deep Knowledge tracing with transformers
缺少学习特征改进
DKT-FE（DKT with feature engineering）
Zhang Liang, Xiong Xiaolu, Zhao Siyuan, et al. Incorporating rich features into deep knowledge tracing
DKT-DT（DKT with decision trees）
Yang Haiqin, Cheung L P. Implicit heterogeneous features embedding in deep knowledge tracing
DKVMN-DT（DKVMN with decision trees）
Sun Xia, Zhao Xu, Ma Yuan, et al. Multi-behavior features based knowledge tracking using decision tree improved DKVMN
DKT + forgetting
Nagatani K, Zhang Qian, Sato M, et al. Augmenting knowledge tracing byconsidering forgetting behavior
AKT（adaptable KT）
Cheng Song, Liu Qi, Chen Enhong. Domain adaption for knowledge tracing
EHFKT （exercise hierarchical feature enhanced KT）
Devlin J, Chang Mingwei, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding
LSTMCQ （ LSTM based contextualized Q-matrix）
Huo Yujia, Wong D F, Ni L M, et al. Knowledge modeling via contextualized representations for LSTM-based personalized exercise
recommendation
DKT-DSC （ DKT with dynamic student classification）/DSCMN（dynamic student classification on memory networks）
Minn S, Yu Yi, Desmarais M C, et al. Deep knowledge tracing and dynamic student classification for knowledge tracing
Minn S, Desmarais M C, Zhu Ferida, et al. Dynamic student classification on memory networks for knowledge tracing
Colearn
Chaudhry R, Singh H, Dogga P, et al. Modeling hint-taking behavior and knowledge state of students with multi-task learning
PDKT-C (prerequisite-driven DKT with constraint modeling）
Chen Penghe, Lu Yu, Zheng V W, et al. Prerequisite-driven deep knowledge tracing
DKT-S（DKT with side information）
Wang Zhiwei, Feng Xiaoqin, Tang Jiliang, et al. Deep knowledge tracing with side information
DHKT（deep hierarchical KT）
Wang Tianqi, Ma Fenghong, Gao Jing. Deep hierarchical knowledge tracing
qDKT（question-centric DKT）
Sonkar S, Waters A E, Lan A S, et al. qDKT: Question-centric deep knowledge tracing
GKT（graph based KT）
Nakagawa H, Iwasawa Y, Matsuo Y. Graph-based knowledge tracing: Modeling student proficiency using graph neural network
CKT（convolutional KT）
Shen Shuanghong, Liu Qi, Chen Enhong, et al. Convolutional knowledge tracing: Modeling individualization in student learning process
SKVMN （sequential key-value memory networks）
Abdelrahman G, Wang Qing. Knowledge tracing with sequential key-value memory networks
DeepFM（deep factorization machines）
Vie J J. Deep factorization machines for knowledge tracing
KTM-DLF（knowledge tracing machine by modeling cognitive item difficulty and learning and forgetting）
Gan Wenbin, Sun Yuan, Peng Xian, et al. Modeling learner’s dynamic knowledge construction procedure and cognitive item difficulty for knowledge tracing
DynEMb
Xu Liangbei, Davenport M A. Dynamic Knowledge embedding and tracing
BDKT （Bayesian neural network DKT）
Donghua Li, Yanming Jia, Jian Zhou, et al. Deep knowledge tracing based on Bayesian neural network
Q-Embedding
Nakagawa H, Iwasawa Y, Matsuo Y. End-to-end deep knowledge tracing by learning binary question-embedding