Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... ·...
Transcript of Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... ·...
![Page 1: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/1.jpg)
Convolutional Knowledge Tracing: ModelingIndividualization in Student Learning Process
Anhui Province Key Lab. of Big Data Analysis and Application, University of S&T ofChina
Shuanghong Shen, Qi Liu, Enhong Chen, Han Wu, Zhenya Huang, Weihao Zhao, Yu Su, Haiping Ma, Shijin Wang
SIGIR 2020
![Page 2: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/2.jpg)
Outline
Ø1. Background
Ø2. Problems and challenges
Ø3. Model architecture
Ø4. Experiments
Ø5. Conclusions
![Page 3: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/3.jpg)
Background
l Benifiting from the technological progress and large-scale application of
online learning systems, such as Coursera and MOOCs, the vast majority of
students have received or are receiving computer-assisted learning.
![Page 4: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/4.jpg)
Background
l Knowledge tracing (KT): an emerging research area under this
context that aims to assess students' changing knowledge state
during learning process.
ü teaching students in accordance with their aptitude
ü maximuming the learning efficiency of students
l Traditional methods
ü BKT: a special case of Hidden Markov Model (HMM)
ü DKT: introduces deep learning into KT, utilizing RNNs or LSTMs
to model students’ knowledge state
ü DKVMN: introduces external memory module to store the
knowledge and update the corresponding knowledge state
![Page 5: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/5.jpg)
Problems and challenges
l Individualization problem
ü Students have different prior knowledge
ü The learning rates differ from student to student
l Without related information given in advance, it is very challenging to measure the individualization of students. We proposed CKT to model the individualization of students with only their learning interactions
![Page 6: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/6.jpg)
Model architecture
l Problem Definition
Given the learning sequence XN = (x1, x2, ..., xt, ..., xN) with N learning
interactions of a student, KT aims to assess the student‘s knowledge
state after each learning interaction. In the learning sequence, xt is an
ordering pair {et, at} , which stands for a learning interaction. Here et
represents the exercise being answered at learning interaction t and at
∈ (0, 1) indicates whether the exercise et has been answered correctly
(1 stands for correct and 0 represents wrong).
![Page 7: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/7.jpg)
Model architecture
l Embedding
l Individualized Prior Knowledgeü Historical Relevant Performance: measuring student historical performance
relevant to the exercise to be answered
ü Concept-wised Percent Correct: accounting for the overall knowledge mastery of student on all knowledge concepts
l Individualized Learning ratedesign hierarchical convolutional layers to extract the learning rate features by processing several continuous learning interactions simultaneously within a sliding window
l Objective Function
![Page 8: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/8.jpg)
Model architecture
![Page 9: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/9.jpg)
Experiments
l Datasets
l Comparison methods• CKT-ONE with only one convolutional layer.• CKT-HRP measures prior knowledge only from HRP.• CKT-CPC measures prior knowledge only from CPC.• CKT-ILR only models individualized learning rate.• CKT-IPK only models individualized prior knowledge.• DKT leverages recurrent neural network to assess student knowledgestate [12]. We utilized LSTM in our implemention.• DKVMN takes advantage of memory network to get interpretablestudent knowledge state.
![Page 10: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/10.jpg)
Experiments
l Student performance prediction
l Visualization of knowledge tracing results
![Page 11: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/11.jpg)
Experiments
l Exercise embeddings learning
![Page 12: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/12.jpg)
Conclusion
l We proposed a novel model called Convolutional Knowledge Tracing (CKT) to mode individualization of students in KT task.
l We measured individualized prior knowledge from students’ historical learning interactions (i.e., HRP andCPC).
l We designed hierarchical convolutional layers to extract individualized learning rates based on continuous learning interactions.
l Extensive experiment results indicated that CKT could get better knowledge tracing results through modeling individualization in student learning process
Code for CKT is available at:https://github.com/bigdata-ustc/Convolutional-Knowledge-Tracing
![Page 13: Convolutional Knowledge Tracing: Modeling ...home.ustc.edu.cn/~huangzhy/files/slides/Shuang... · N) with Nlearning interactions of a student, KT aims to assess the student‘s knowledge](https://reader033.fdocuments.us/reader033/viewer/2022060600/6054ab011ab4ca4cfc5754a3/html5/thumbnails/13.jpg)
Thank you for listening
Q & A