{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T13:48:53Z","timestamp":1780062533887,"version":"3.54.0"},"reference-count":33,"publisher":"SAGE Publications","issue":"1-2","license":[{"start":{"date-parts":[[2021,10,28]],"date-time":"2021-10-28T00:00:00Z","timestamp":1635379200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Web Intelligence"],"published-print":{"date-parts":[[2021,12,3]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3233\/web-210458","type":"journal-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T11:41:05Z","timestamp":1635507665000},"page":"87-102","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":30,"title":["Graph-based knowledge tracing: Modeling student proficiency using graph neural networks"],"prefix":"10.1177","volume":"19","author":[{"given":"Hiromi","family":"Nakagawa","sequence":"first","affiliation":[{"name":"Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails:\u00a0,\u00a0,\u00a0"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuke","family":"Iwasawa","sequence":"additional","affiliation":[{"name":"Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails:\u00a0,\u00a0,\u00a0"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutaka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"Department of Engineering, The University of Tokyo, Tokyo, Japan. E-mails:\u00a0,\u00a0,\u00a0"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2021,10,28]]},"reference":[{"key":"ref001","doi-asserted-by":"crossref","unstructured":"M.\u00a0Bastian, S.\u00a0Heymann and M.\u00a0Jacomy, Gephi: An Open Source Software for Exploring and Manipulating Networks, 2009, http:\/\/www.aaai.org\/ocs\/index.php\/ICWSM\/09\/paper\/view\/154.","DOI":"10.1609\/icwsm.v3i1.13937"},{"key":"ref002","unstructured":"P.\u00a0Battaglia, R.\u00a0Pascanu, M.\u00a0Lai, D.\u00a0Jimenez Rezende et al., Interaction networks for learning about objects, relations and physics, in: Advances in Neural Information Processing Systems, 2016, pp.\u00a04502\u20134510."},{"key":"ref003","unstructured":"P.W.\u00a0Battaglia, J.B.\u00a0Hamrick, V.\u00a0Bapst, A.\u00a0Sanchez-Gonzalez, V.\u00a0Zambaldi, M.\u00a0Malinowski, A.\u00a0Tacchetti, D.\u00a0Raposo, A.\u00a0Santoro, R.\u00a0Faulkner et al., Relational inductive biases, deep learning, and graph networks, 2018, Preprint, arXiv:1806.01261."},{"key":"ref004","unstructured":"H.S.\u00a0Chang, H.J.\u00a0Hsu and K.T.\u00a0Chen, Modeling exercise relationships in E-learning: A unified approach, in: EDM, 2015, pp.\u00a0532\u2013535."},{"key":"ref005","unstructured":"Z.\u00a0Chen, L.\u00a0Li and J.\u00a0Bruna, Supervised Community Detection with Line Graph Neural Networks, 2018."},{"key":"ref006","doi-asserted-by":"crossref","unstructured":"K.\u00a0Cho, B.\u00a0Van Merri\u00ebnboer, C.\u00a0Gulcehre, D.\u00a0Bahdanau, F.\u00a0Bougares, H.\u00a0Schwenk and Y.\u00a0Bengio, Learning phrase representations using rnn encoder-decoder for statistical machine translation, 2014, Preprint, arXiv:1406.1078.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref007","unstructured":"D.A.\u00a0Clevert, T.\u00a0Unterthiner and S.\u00a0Hochreiter, Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs), 2015, Preprint, arXiv:1511.07289."},{"key":"ref008","doi-asserted-by":"publisher","DOI":"10.1007\/BF01099821"},{"key":"ref009","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-009-9063-7"},{"key":"ref010","unstructured":"A.\u00a0Fout, J.\u00a0Byrd, B.\u00a0Shariat and A.\u00a0Ben-Hur, Protein interface prediction using graph convolutional networks, in: Advances in Neural Information Processing Systems, 2017, pp.\u00a06530\u20136539."},{"key":"ref011","unstructured":"J.\u00a0Gilmer, S.S.\u00a0Schoenholz, P.F.\u00a0Riley, O.\u00a0Vinyals and G.E.\u00a0Dahl, Neural message passing for quantum chemistry, 2017, Preprint, arXiv:1704.01212."},{"key":"ref012","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref013","unstructured":"W.\u00a0Hamilton, Z.\u00a0Ying and J.\u00a0Leskovec, Inductive representation learning on large graphs, in: Advances in Neural Information Processing Systems, 2017, pp.\u00a01024\u20131034."},{"key":"ref014","unstructured":"S.\u00a0Ioffe and C.\u00a0Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, 2015, Preprint, arXiv:1502.03167."},{"key":"ref015","unstructured":"D.\u00a0Kingma and J.\u00a0Ba, Adam: A method for stochastic optimization, 2014, Preprint, arXiv:1412.6980."},{"key":"ref016","unstructured":"D.P.\u00a0Kingma and M.\u00a0Welling, Auto-encoding variational bayes, 2013, Preprint, arXiv:1312.6114."},{"key":"ref017","unstructured":"T.\u00a0Kipf, E.\u00a0Fetaya, K.C.\u00a0Wang, M.\u00a0Welling and R.\u00a0Zemel, Neural relational inference for interacting systems, 2018, Preprint, arXiv:1802.04687."},{"key":"ref018","unstructured":"T.N.\u00a0Kipf and M.\u00a0Welling, Semi-supervised classification with graph convolutional networks, 2016, Preprint, arXiv:1609.02907."},{"key":"ref019","unstructured":"A.\u00a0Krizhevsky, I.\u00a0Sutskever and G.E.\u00a0Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp.\u00a01097\u20131105."},{"key":"ref020","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330922"},{"key":"ref021","unstructured":"C.J.\u00a0Maddison, A.\u00a0Mnih and Y.W.\u00a0Teh, 2016, The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables. Preprint, arXiv:1611.00712."},{"key":"ref022","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26561-2_60"},{"key":"ref023","unstructured":"A.\u00a0Sanchez-Gonzalez, N.\u00a0Heess, J.T.\u00a0Springenberg, J.\u00a0Merel, M.\u00a0Riedmiller, R.\u00a0Hadsell and P.\u00a0Battaglia, Graph networks as learnable physics engines for inference and control, 2018, Preprint, arXiv:1806.01242."},{"key":"ref024","unstructured":"J.\u00a0Stamper, A.\u00a0Niculescu-Mizil, S.\u00a0Ritter, G.J.\u00a0Gordon and K.R.\u00a0Koedinger, 2010a. Algebra I 2005\u20132006. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http:\/\/pslcdatashop.web.cmu.edu\/KDDCup\/downloads.jsp."},{"key":"ref025","unstructured":"J.\u00a0Stamper, A.\u00a0Niculescu-Mizil, S.\u00a0Ritter, G.J.\u00a0Gordon and K.R.\u00a0Koedinger, 2010b. Algebra I 2006\u20132007. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http:\/\/pslcdatashop.web.cmu.edu\/KDDCup\/downloads.jsp."},{"key":"ref026","unstructured":"J.\u00a0Stamper, A.\u00a0Niculescu-Mizil, S.\u00a0Ritter, G.J.\u00a0Gordon and K.R.\u00a0Koedinger, 2010c. Bridge to Algebra 2006\u20132007. Development data set from KDD Cupucational Data Mining Challenge, 2010th edn, http:\/\/pslcdatashop.web.cmu.edu\/KDDCup\/downloads.jsp."},{"key":"ref027","unstructured":"A.\u00a0Vaswani, N.\u00a0Shazeer, N.\u00a0Parmar, J.\u00a0Uszkoreit, L.\u00a0Jones, A.N.\u00a0Gomez, \u0141.\u00a0Kaiser and I.\u00a0Polosukhin, Attention is all you need, in: Advances in Neural Information Processing Systems, 2017, pp.\u00a05998\u20136008."},{"key":"ref028","unstructured":"P.\u00a0Velickovic, G.\u00a0Cucurull, A.\u00a0Casanova, A.\u00a0Romero, P.\u00a0Lio and Y.\u00a0Bengio, Graph attention networks, Vol.\u00a01, 2017, p.\u00a02, Preprint, arXiv:1710.10903."},{"key":"ref029","doi-asserted-by":"crossref","unstructured":"L.\u00a0Wang, A.\u00a0Sy, L.\u00a0Liu and C.\u00a0Piech, Deep knowledge tracing on programming exercises, in: Proceedings of the Fourth, ACM Conference on Learning@ Scale, ACM, 2017, pp.\u00a0201\u2013204.","DOI":"10.1145\/3051457.3053985"},{"key":"ref030","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang, R.\u00a0Girshick, A.\u00a0Gupta and K.\u00a0He, Non-local neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp.\u00a07794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref031","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref032","doi-asserted-by":"crossref","unstructured":"S.\u00a0Wu, Y.\u00a0Tang, Y.\u00a0Zhu, L.\u00a0Wang, X.\u00a0Xie and T.\u00a0Tan, Session-based recommendation with graph neural networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol.\u00a033, 2019, pp.\u00a0346\u2013353.","DOI":"10.1609\/aaai.v33i01.3301346"},{"key":"ref033","doi-asserted-by":"crossref","unstructured":"J.\u00a0Zhang, X.\u00a0Shi, I.\u00a0King and D.Y.\u00a0Yeung, Dynamic Key-Value Memory Network for Knowledge Tracing, 2016, Preprint, arXiv:1611.08108.","DOI":"10.1145\/3038912.3052580"}],"container-title":["Web Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/WEB-210458","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/WEB-210458","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/WEB-210458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:27:23Z","timestamp":1777613243000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/WEB-210458"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,28]]},"references-count":33,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2021,12,3]]}},"alternative-id":["10.3233\/WEB-210458"],"URL":"https:\/\/doi.org\/10.3233\/web-210458","relation":{},"ISSN":["2405-6456","2405-6464"],"issn-type":[{"value":"2405-6456","type":"print"},{"value":"2405-6464","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,28]]}}}