Graph-based knowledge tracing: Modeling student proficiency using graph neural networks

Hiromi Nakagawa; Yusuke Iwasawa; Yutaka Matsuo

doi:10.3233/web-210458

journal article Oct 28, 2021

Graph-based knowledge tracing: Modeling student proficiency using graph neural networks

Hiromi Nakagawa Yusuke Iwasawa Yutaka Matsuo

Web Intelligence Vol. 19 No. 1-2 pp. 87-102 · SAGE Publications

View at Publisher Save 10.3233/web-210458

Abstract

Recent advancements in computer-assisted learning systems have caused an increase in the research in knowledge tracing, wherein student performance is predicted over time. Student coursework can potentially be structured as a graph. Incorporating this graph-structured nature into a knowledge tracing model as a relational inductive bias can improve its performance; however, previous methods, such as deep knowledge tracing, did not consider such a latent graph structure. Inspired by the recent successes of graph neural networks (GNNs), we herein propose a GNN-based knowledge tracing method, i.e., graph-based knowledge tracing. Casting the knowledge structure as a graph enabled us to reformulate the knowledge tracing task as a time-series node-level classification problem in the GNN. As the knowledge graph structure is not explicitly provided in most cases, we propose various implementations of the graph structure. Empirical validations on two open datasets indicated that our method could potentially improve the prediction of student performance and demonstrated more interpretable predictions compared to those of the previous methods, without the requirement of any additional information.

Topics

No keywords indexed for this article. Browse by subject →

References

33

[1]

Gephi: An Open Source Software for Exploring and Manipulating Networks

Mathieu Bastian, Sebastien Heymann, Mathieu Jacomy

Proceedings of the International AAAI Conference o... 10.1609/icwsm.v3i1.13937

[2]

P. Battaglia, R. Pascanu, M. Lai, D. Jimenez Rezende et al., Interaction networks for learning about objects, relations and physics, in: Advances in Neural Information Processing Systems, 2016, pp. 4502–4510.

[3]

P.W. Battaglia, J.B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner et al., Relational inductive biases, deep learning, and graph networks, 2018, Preprint, arXiv:1806.01261.

[4]

H.S. Chang, H.J. Hsu and K.T. Chen, Modeling exercise relationships in E-learning: A unified approach, in: EDM, 2015, pp. 532–535.

[5]

Z. Chen, L. Li and J. Bruna, Supervised Community Detection with Line Graph Neural Networks, 2018.

[6]

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre et al.

Proceedings of the 2014 Conference on Empirical Me... 10.3115/v1/d14-1179

[7]

D.A. Clevert, T. Unterthiner and S. Hochreiter, Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs), 2015, Preprint, arXiv:1511.07289.

[8]

Knowledge tracing: Modeling the acquisition of procedural knowledge

Albert T. Corbett, John R. Anderson

User Modeling and User-Adapted Interaction 10.1007/bf01099821

[9]

10.1007/s11257-009-9063-7

[10]

A. Fout, J. Byrd, B. Shariat and A. Ben-Hur, Protein interface prediction using graph convolutional networks, in: Advances in Neural Information Processing Systems, 2017, pp. 6530–6539.

[11]

J. Gilmer, S.S. Schoenholz, P.F. Riley, O. Vinyals and G.E. Dahl, Neural message passing for quantum chemistry, 2017, Preprint, arXiv:1704.01212.

[12]

10.1109/ijcnn.2005.1555942

[13]

W. Hamilton, Z. Ying and J. Leskovec, Inductive representation learning on large graphs, in: Advances in Neural Information Processing Systems, 2017, pp. 1024–1034.

[14]

S. Ioffe and C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 2015, Preprint, arXiv:1502.03167.

[15]

D. Kingma and J. Ba, Adam: A method for stochastic optimization, 2014, Preprint, arXiv:1412.6980.

[16]

D.P. Kingma and M. Welling, Auto-encoding variational bayes, 2013, Preprint, arXiv:1312.6114.

[17]

T. Kipf, E. Fetaya, K.C. Wang, M. Welling and R. Zemel, Neural relational inference for interacting systems, 2018, Preprint, arXiv:1802.04687.

[18]

T.N. Kipf and M. Welling, Semi-supervised classification with graph convolutional networks, 2016, Preprint, arXiv:1609.02907.

[19]

A. Krizhevsky, I. Sutskever and G.E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp. 1097–1105.

[20]

10.1145/3292500.3330922

[21]

C.J. Maddison, A. Mnih and Y.W. Teh, 2016, The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. Preprint, arXiv:1611.00712.

[22]

10.1007/978-3-319-26561-2_60

[23]

A. Sanchez-Gonzalez, N. Heess, J.T. Springenberg, J. Merel, M. Riedmiller, R. Hadsell and P. Battaglia, Graph networks as learnable physics engines for inference and control, 2018, Preprint, arXiv:1806.01242.

[24]

J. Stamper, A. Niculescu-Mizil, S. Ritter, G.J. Gordon and K.R. Koedinger, 2010a. Algebra I 2005–2006. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http://pslcdatashop.web.cmu.edu/KDDCup/downloads.jsp.

[25]

J. Stamper, A. Niculescu-Mizil, S. Ritter, G.J. Gordon and K.R. Koedinger, 2010b. Algebra I 2006–2007. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http://pslcdatashop.web.cmu.edu/KDDCup/downloads.jsp.

[26]

J. Stamper, A. Niculescu-Mizil, S. Ritter, G.J. Gordon and K.R. Koedinger, 2010c. Bridge to Algebra 2006–2007. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http://pslcdatashop.web.cmu.edu/KDDCup/downloads.jsp.

[27]

A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, Ł. Kaiser and I. Polosukhin, Attention is all you need, in: Advances in Neural Information Processing Systems, 2017, pp. 5998–6008.

[28]

P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio and Y. Bengio, Graph attention networks, Vol. 1, 2017, p. 2, Preprint, arXiv:1710.10903.

[29]

L. Wang, A. Sy, L. Liu and C. Piech, Deep knowledge tracing on programming exercises, in: Proceedings of the Fourth, ACM Conference on Learning@ Scale, ACM, 2017, pp. 201–204. 10.1145/3051457.3053985

[30]

Non-local Neural Networks

Xiaolong Wang, Ross Girshick, Abhinav Gupta et al.

2018 IEEE/CVF Conference on Computer Vision and Pa... 10.1109/cvpr.2018.00813

[31]

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

Ronald J. Williams, David Zipser

Neural Computation 10.1162/neco.1989.1.2.270

[32]

Session-Based Recommendation with Graph Neural Networks

Shu Wu, Yuyuan Tang, Yanqiao Zhu et al.

Proceedings of the AAAI Conference on Artificial I... 10.1609/aaai.v33i01.3301346

[33]

J. Zhang, X. Shi, I. King and D.Y. Yeung, Dynamic Key-Value Memory Network for Knowledge Tracing, 2016, Preprint, arXiv:1611.08108. 10.1145/3038912.3052580

Metrics

25

Citations

33

References

Details

Published: Oct 28, 2021
Vol/Issue: 19(1-2)
Pages: 87-102
License: View

Authors

H

Hiromi Nakagawa

Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails: , ,

Y

Yusuke Iwasawa

Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails: , ,

Y

Yutaka Matsuo

Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails: , ,

Cite This Article

Hiromi Nakagawa, Yusuke Iwasawa, Yutaka Matsuo (2021). Graph-based knowledge tracing: Modeling student proficiency using graph neural networks. Web Intelligence, 19(1-2), 87-102. https://doi.org/10.3233/web-210458

Graph-based knowledge tracing: Modeling student proficiency using graph neural networks

You May Also Like