RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems

Cognitive diagnosis (CD) is a fundamental issue in intelligent educational settings, which aims to discover the mastery levels of students on different knowledge concepts. In general, most previous works consider it as an inter-layer interaction modeling problem, e.g., student-exercise interactions in IRT or student-concept interactions in DINA, while the inner-layer structural relations, such as educational interdependencies among concepts, are still underexplored. Furthermore, there is a lack of comprehensive modeling for the student-exercise-concept hierarchical relations in CD systems. To this end, in this paper, we present a novel Relation map driven Cognitive Diagnosis (RCD) framework, uniformly modeling the interactive and structural relations via a multi-layer student-exercise-concept relation map. Specifically, we first represent students, exercises and concepts as individual nodes in a hierarchical layout, and construct three well-defined local relation maps to incorporate inter- and inner-layer relations, including a student-exercise interaction map, a concept-exercise correlation map and a concept dependency map. Then, we leverage a multi-level attention network to integrate node-level relation aggregation inside each local map and balance map-level aggregation across different maps. Finally, we design an extendable diagnosis function to predict students' performance and jointly train the networks. Extensive experimental results on real-world datasets clearly show the effectiveness and extendibility of our RCD in both diagnosis accuracy improvement and relation-aware representation learning.

[1]  Jaideep Srivastava,et al.  RKT: Relation-Aware Self-Attention for Knowledge Tracing , 2020, CIKM.

[2]  ChenEnhong,et al.  Learning or Forgetting? A Dynamic Approach for Tracking the Knowledge Proficiency of Students , 2020 .

[3]  J. de la Torre.  DINA Model and Parameter Estimation: A Didactic , 2009 .

[4]  Enhong Chen,et al.  Structure-based Knowledge Tracing: An Influence Propagation View , 2020, 2020 IEEE International Conference on Data Mining (ICDM).

[5]  Jian Pei,et al.  A Survey on Network Embedding , 2017, IEEE Transactions on Knowledge and Data Engineering.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Hao Wang,et al.  MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network , 2019, KDD.

[8]  Lei Dong,et al.  Group Sparse Bayesian Learning for Active Surveillance on Epidemic Dynamics , 2017, AAAI.

[9]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[10]  Joseph D. Novak,et al.  Learning creating and using knowledge: Concept maps as facilitative tools , 1998 .

[11]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[12]  Mark J. Gierl,et al.  Using Multidimensional Item Response Theory to Evaluate Educational and Psychological Tests , 2005 .

[13]  Huan Liu,et al.  Interactive Unknowns Recommendation in E-Learning Systems , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[14]  Kent McClelland.  Understanding Curriculum: An Introduction to the Study of Historical and Contemporary Curriculum Discourses , 2003 .

[15]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[16]  Christopher D. Manning,et al.  Graph Convolution over Pruned Dependency Trees Improves Relation Extraction , 2018, EMNLP.

[17]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[18]  Hui Xiong,et al.  EKT: Exercise-Aware Knowledge Tracing for Student Performance Prediction , 2019, IEEE Transactions on Knowledge and Data Engineering.

[19]  Meng Wang,et al.  Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach , 2020, AAAI.

[20]  Michael Jahrer,et al.  Collaborative Filtering Applied to Educational Data Mining , 2010 .

[21]  Michael C. Mozer,et al.  Integrating latent-factor and knowledge-tracing models to predict individual differences in learning , 2014, EDM.

[22]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[23]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[24]  Terry A. Ackerman.  Multidimensional Item Response Theory Models , 2005 .

[25]  J. D. L. Torre,et al.  DINA Model and Parameter Estimation: A Didactic , 2009 .

[26]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[27]  Haiqin Yang,et al.  Implicit Heterogeneous Features Embedding in Deep Knowledge Tracing , 2018, Cognitive Computation.

[28]  Yutaka Matsuo,et al.  Graph-based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network , 2019, 2019 IEEE/WIC/ACM International Conference on Web Intelligence (WI).

[29]  Zhiwei Wang,et al.  Deep Knowledge Tracing with Side Information , 2019, AIED.

[30]  Enhong Chen,et al.  Exploring Multi-Objective Exercise Recommendations in Online Education Systems , 2019, CIKM.

[31]  Jaewoo Kang,et al.  Graph Transformer Networks , 2019, NeurIPS.

[32]  Yongdong Zhang,et al.  LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation , 2020, SIGIR.

[33]  Raymond J. Adams,et al.  The Multidimensional Random Coefficients Multinomial Logit Model , 1997 .

[34]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[35]  J. Piaget,et al.  The equilibration of cognitive structures : the central problem of intellectual development , 1985 .

[36]  Enhong Chen,et al.  Fuzzy Cognitive Diagnosis for Modelling Examinee Performance , 2018, ACM Trans. Intell. Syst. Technol..

[37]  David Engel,et al.  Intelligent Tutoring Systems Evolutions In Design , 2016 .

[38]  Hongchi Shi,et al.  An intelligent distributed environment for active learning , 2001, JERC.

[39]  Jure Leskovec,et al.  Engaging with massive online courses , 2014, WWW.

[40]  Christine E. DeMars,et al.  Item Response Theory , 2010, Assessing Measurement Invariance for Applied Research.

[41]  Nitesh V. Chawla,et al.  Heterogeneous Graph Neural Network , 2019, KDD.

[42]  Enhong Chen,et al.  Neural Cognitive Diagnosis for Intelligent Education Systems , 2019, AAAI.

[43]  Enhong Chen,et al.  Constructing Educational Concept Maps with Multiple Relationships from Multi-Source Data , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[44]  Penghe Chen,et al.  Prerequisite-Driven Deep Knowledge Tracing , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[45]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[46]  E. Thorndike,et al.  The influence of improvement in one mental function upon the efficiency of other functions. (I). , 1901 .

[47]  Zhengyang Wang,et al.  Large-Scale Learnable Graph Convolutional Networks , 2018, KDD.

[48]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[49]  Enhong Chen,et al.  Quality meets Diversity: A Model-Agnostic Framework for Computerized Adaptive Testing , 2020, 2020 IEEE International Conference on Data Mining (ICDM).

[50]  Yanfang Ye,et al.  Heterogeneous Graph Attention Network , 2019, WWW.

[51]  A. A. G. Putra,et al.  PIECING TOGETHER THE STUDENT SUCCESS PUZZLE: RESEARCH, PROPOSITIONS, AND RECOMMENDATIONS , 2013 .