计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 173-180.doi: 10.11896/jsjkx.211200134

• 数据库&大数据&数据科学 • 上一篇    下一篇


董永峰1,2,3, 黄港1,2,3, 薛婉若1, 李林昊1,2,3   

  1. 1 河北工业大学人工智能与数据科学学院 天津 300401
    2 河北省大数据计算重点实验室 天津 300401
    3 河北省数据驱动工业智能工程研究中心 天津 300401
  • 收稿日期:2021-12-13 修回日期:2022-06-01 出版日期:2023-03-15 发布日期:2023-03-15
  • 通讯作者: 李林昊(lilinhao@hebut.edu.cn)
  • 作者简介:(dongyf@hebut.edu.cn)
  • 基金资助:
    国家自然科学基金(61902106,61806072);河北省高等教育教学改革研究与实践项目(2020GJJG027); 河北省自然科学基金(F2020202028)

Graph Attention Deep Knowledge Tracing Model Integrated with IRT

DONG Yongfeng1,2,3, HUANG Gang1,2,3, XUE Wanruo1, LI Linhao1,2,3   

  1. 1 School of Artifcial Intelligence,Hebei University of Technology,Tianjin 300401,China
    2 Hebei Key Laboratory of Big Data Computing,Tianjin 300401,China
    3 Hebei Engineering Research Center of Data-Driven Industrial Intelligent,Tianjin 300401,China
  • Received:2021-12-13 Revised:2022-06-01 Online:2023-03-15 Published:2023-03-15
  • About author:DONG Yongfeng,born in 1977,Ph.D,professor,is a member of China Computer Federation.His main research interets include intelligent information processing,big data technology,robo-tics and intelligent control,and software engineering.
    LI Linhao,born in 1989,Ph.D,lecturer,is a member of China Computer Federation.His main research interests include quantization and hash learning,sparse signal recovery,background modeling and foreground detection.
  • Supported by:
    National Natural Science Foundation of China(61902106,61806072),Hebei Province Higher Education Teaching Reform Research and Practice Project(2020GJJG027) andNatural Science Foundation of Hebei Province(F2020202028).

摘要: 知识追踪,旨在根据学生的历史答题表现实时追踪学生的知识状态(知识的掌握程度)并且预测学生未来的答题表现。目前的研究仅仅探索了问题或概念本身对学生答题表现的直接影响,而往往忽略了问题及包含的概念中存在的深层次信息对学生答题表现的间接影响。为了更好地利用这些深层次信息,一种融合项目反应理论的图注意力深度知识追踪模型GAKT-IRT被提出。模型将图注意力网络应用于知识追踪领域,取得了显著的提升效果,并使用IRT增加了模型的可解释性。首先,通过图注意力网络层获得问题的深层次特征表示;接着,根据结合了深层次信息的学生历史答题序列对学生的知识状态进行建模;然后,使用IRT对学生未来的答题表现进行预测。在6个公开真实在线教育数据集上的对比实验结果证明了,GAKT-IRT模型可以更好地完成知识追踪任务,在预测学生未来答题表现上具有明显的优势。

关键词: 知识追踪, 图注意力网络, 项目反应理论, 深度学习, 可解释性

Abstract: Knowledge tracing aims to trace students’ knowledge state(the degree of knowledge) based on their historical answer performance in real time and predict their future answer performance.The current research only explores the direct influence of the question or concept itself on the performance of students’ answering questions,while often ignores the indirect influence of the deep-level information in the questions and the concepts contained on the performance of students’ answering questions.In order to make better use of these deep-level information,a graph attention deep knowledge tracing model integrated with IRT(GAKT-IRT) is proposed,which integrates item response theory(IRT).The graph attention network is applied to the field of knowledge tracing and uses IRT to increase the interpretability of the model.First,obtain the deep-level feature representation of the problem through the graph attention network layer.Next,model students’ knowledge state based on their historical answer sequence that combines the in-depth information.Then,use IRT to predict students’ future answer performance.Results of comparative experiments on 6 open real online education datasets prove that the GAKT-IRT model can better complete the knowledge tracing task and has obvious advantages in predicting the future performance of students in answering questions.

Key words: Knowledge tracing, Graph attention network, Item response theory, Deep learning, Interpretability


  • TP391.6
[1]ANDERSON A,HUTTENLOCHER D,KLEINBERG J,et al.Engaging with massive online courses[C]//Proceedings of the 23rd International Conference on World Wide Web.2014:687-698.
[2]VIE J J.Knowledge Tracing Machines:Towards an Unification of DKT,IRT & PFA[C]//ITS Workshops.2018:149.
[3]INJADAT M N,MOUBAYED A,NASSIF A B,et al.Systema-tic Ensemble Model Selection Approach for Educational Data Mining[J].Knowledge-Based Systems,2020,200:105992.
[4]PIECH C,SPENCER J,HUANG J,et al.Deep knowledge tra-cing[J].arXiv:1506.05908,2015.
[5]ZHANG J,SHI X,KING I,et al.Dynamic key-value memorynetworks for knowledge tracing[C]//Proceedings of the 26th International Conference on World Wide Web.2017:765-774.
[6]SHEN S,LIU Q,CHEN E,et al.Convolutional knowledge tra-cing:Modeling individualization in student learning process[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:1857-1860.
[7]YEUNG C K.Deep-IRT:Make deep learning based knowledge tracing explainable using item response theory[J].arXiv:1904.11738,2019.
[8]SU Y,LIU Q,LIU Q,et al.Exercise-enhanced sequential mode-ling for student performance prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018.
[9]LIU Q,HUANG Z,YIN Y,et al.Ekt:Exercise-aware know-ledge tracing for student performance prediction[J].IEEE Transactions on Knowledge and Data Engineering,2019,33(1):100-115.
[10]ABDELRAHMAN G,WANG Q.Knowledge tracing with se-quential key-value memory networks[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:175-184.
[11]CORBETT A T,ANDERSON J R.Knowledge tracing:Mode-ling the acquisition of procedural knowledge[J].User Modeling and User-adapted Interaction,1994,4(4):253-278.
[12]PAVLIK JR P I,CEN H,KOEDINGER K R.Performance Factors Analysis-A New Alternative to Knowledge Tracing[J].Online Submission,2009,15(3):513-521.
[13]VIE J J,KASHIMA H.Knowledge tracing machines:Factorization machines for knowledge tracing[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:750-757.
[14]RENDLE S.Factorization machines[C]//2010 IEEE Interna-tional Conference on Data Mining.IEEE,2010:995-1000.
[15]CHEN P,LU Y,ZHENG V W,et al.Prerequisite-driven deep knowledge tracing[C]//2018 IEEE International Conference on Data Mining(ICDM).IEEE,2018:39-48.
[16]MINN S,YU Y,DESMARAIS M C,et al.Deep knowledge tra-cing and dynamic student classification for knowledge tracing[C]//2018 IEEE International Conference on Data Mining(ICDM).IEEE,2018:1182-1187.
[17]GHOSH A,HEFFERNAN N,LAN A S.Context-aware attentive knowledge tracing[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:2330-2339.
[18]LI X G,WEI S Q,ZHANG X,et al.LFKT:Deep knowledgetracing model with learning and forgetting behavior merging[J].Journal of Software,2021,32(3):818-830.
[19]WANG C,LIU Z H,WANG B,et al.TCN-KT:temporal convolutional knowledge tracking model based on fusion of personal basis and forgetting[J].Application Research of Computers,2022,23(2):1-6.
[20]LIU Y,YANG Y,CHEN X,et al.Improving knowledge tracing via pre-training question embeddings[J].arXiv:2012.05031,2020.
[21]NAKAGAWA H,IWASAWA Y,MATSUO Y.Graph-basedknowledge tracing:modeling student proficiency using graph neural network[C]//2019 IEEE/WIC/ACM International Conference on Web Intelligence(WI).IEEE,2019:156-163.
[22]WANG B,SHENG Y X,JI X Y.DKTwMF:A deep knowledge tracing with multiple features[J].Computer Technology and Development,2021,31(7):35-41.
[23]HUANG S W,LIU Z H,LUO L Y,et al.behavior-forgettingBayesian knowledge tracing[J].Application Research of Computers,2021,38(7):1993-1997.
[24]KEAN J,REILLY J.Item response theory[C]//Handbook for Clinical Research:Design,Statistics and Implementation.2014:195-198.
[25]BIRNBAUM A L.Some latent trait models and their use in inferring an examinee's ability[M].New York:Statistical Theories of Mental Test Scores,1968.
[26]KETKAR N.Convolutional neural networks[M]//Deep Lear-ning with Python.Apress,Berkeley,CA,2017:63-78.
[27]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[28]VELIČKOVIY' P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[29]QIN C,ZHANG Y,LIU Y,et al.A visual place recognition approach using learnable feature map filtering and graph attention networks[J].Neurocomputing,2021,457:277-292.
[30]XIAO Y,PEI Q,XIAO T,et al.MutualRec:Joint friend anditem recommendations with mutualistic attentional graph neural networks[J].Journal of Network and Computer Applications,2021,177:102954.
[31]LI Q,LIN W,LIU Z,et al.Message-aware graph attention networks for large-scale multi-robot path planning[J].IEEE Robotics and Automation Letters,2021,6(3):5533-5540.
[32]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Advances in Neural Information Processing Systems.2017:5998-6008.
[33]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[34]SU Y,CHENG Z,LUO P,et al.Time-and-Concept EnhancedDeep Multidimensional Item Response Theory for interpretable Knowledge Tracing[J].Knowledge-Based Systems,2021,218:106819.
[35]XIONG X,ZHAO S,VAN INWEGEN E G,et al.Going deeper with deep knowledge tracing[C]//Proceedings of the 9th International Conference on Educational Data Mining.2016:545-550.
[1] 华晓凤, 冯娜, 于俊清, 何云峰.
Shooting Event Detection of Free Kick in Soccer Video Based on Rule Reasoning
计算机科学, 2023, 50(3): 181-190. https://doi.org/10.11896/jsjkx.220300062
[2] 梅鹏程, 杨吉斌, 张强, 黄翔.
Sound Event Joint Estimation Method Based on Three-dimension Convolution
计算机科学, 2023, 50(3): 191-198. https://doi.org/10.11896/jsjkx.220500259
[3] 白雪飞, 马亚楠, 王文剑.
Segmentation Method of Edge-guided Breast Ultrasound Images Based on Feature Fusion
计算机科学, 2023, 50(3): 199-207. https://doi.org/10.11896/jsjkx.211200294
[4] 刘航, 普园媛, 吕大华, 赵征鹏, 徐丹, 钱文华.
Polarized Self-attention Constrains Color Overflow in Automatic Coloring of Image
计算机科学, 2023, 50(3): 208-215. https://doi.org/10.11896/jsjkx.220100149
[5] 陈亮, 王璐, 李生春, 刘昌宏.
Study on Visual Dashboard Generation Technology Based on Deep Learning
计算机科学, 2023, 50(3): 238-245. https://doi.org/10.11896/jsjkx.230100064
[6] 张译, 吴秦.
Crowd Counting Network Based on Feature Enhancement Loss and Foreground Attention
计算机科学, 2023, 50(3): 246-253. https://doi.org/10.11896/jsjkx.220100219
[7] 应宗浩, 吴槟.
Backdoor Attack on Deep Learning Models:A Survey
计算机科学, 2023, 50(3): 333-350. https://doi.org/10.11896/jsjkx.220600031
[8] 邹芸竹, 杜圣东, 滕飞, 李天瑞.
Visual Question Answering Model Based on Multi-modal Deep Feature Fusion
计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303
[9] 王鹏宇, 台文鑫, 刘芳, 钟婷, 罗绪成, 周帆.
Self-supervised Flight Trajectory Prediction Based on Data Augmentation
计算机科学, 2023, 50(2): 130-137. https://doi.org/10.11896/jsjkx.211200016
[10] 郭楠, 李婧源, 任曦.
Survey of Rigid Object Pose Estimation Algorithms Based on Deep Learning
计算机科学, 2023, 50(2): 178-189. https://doi.org/10.11896/jsjkx.211200164
[11] 李俊林, 欧阳智, 杜逆索.
Scene Text Detection with Improved Region Proposal Network
计算机科学, 2023, 50(2): 201-208. https://doi.org/10.11896/jsjkx.211000191
[12] 华杰, 刘学亮, 赵烨.
Few-shot Object Detection Based on Feature Fusion
计算机科学, 2023, 50(2): 209-213. https://doi.org/10.11896/jsjkx.220500153
[13] 李炜卓, 卢冰洁, 杨骏铭, 那崇宁.
Study on Abductive Analysis of Auto Insurance Fraud Based on Network Representation Learning
计算机科学, 2023, 50(2): 300-309. https://doi.org/10.11896/jsjkx.220800169
[14] 梁佳利, 华保健, 苏少博.
Tensor Instruction Generation Optimization Fusing with Loop Partitioning
计算机科学, 2023, 50(2): 374-383. https://doi.org/10.11896/jsjkx.220300147
[15] 王少将, 刘佳, 郑锋, 潘祎诚.
Survey on Hierarchical Clustering for Machine Learning
计算机科学, 2023, 50(1): 9-17. https://doi.org/10.11896/jsjkx.211000185
Full text



No Suggested Reading articles found!