Knowledge Tracing (KT) predicts the probability of a student answering the subsequent question correctly based on their past performance, providing an assessment of the mastery of underlying concepts. However, the sparsity of interaction data in KT poses challenges, leading most models to represent questions using concepts and overlooking specific question information. Although the existing graph structure between concepts and questions considers both questions and concepts, current methods predominantly focus on homogeneous or heterogeneous graphs, presupposing a singular edge type linking nodes and neglecting the diverse feature paths within a multiplex heterogeneous network. Addressing these obstacles, the present study presents a model known as Integrating Multiplex Heterogeneous Network for Knowledge Tracing (MHNKT). Treating students and questions as two distinct types of nodes, they are connected through incorrect and correct interactions to construct a multiplex heterogeneous network for student-question. Employing multiplex Heterogeneous Graph Neural Networks (HetGNN), the model learns question representations from heterogeneous node aggregation and multi-type edge aggregation. Additionally, to address the many-to-many relationships between questions and concepts, the question-concept graph is input into a two-layer Graph Convolutional Network (GCN) for acquiring question representations. Results from experiments on four real datasets indicate that the MHNKT model outperforms the baseline model in terms of performance.

[1] Chang H., Hsu H., and Chen K., “Modeling Exercise Relationships in E-Learning: A Unified Approach,” in Proceedings of the 8th International Conference on Educational Data Mining, Madrid, pp. 532-535, 2015. https://www.educationaldatamining.org/EDM201 5/proceedings/short532-535.pdf

[2] Corbett A. and Anderson J., “Knowledge Tracing: Modeling the Acquisition of Procedural Knowledge,” User Modeling and User-Adapted Interaction, vol. 4, pp. 253-278, 1994. https://link.springer.com/article/10.1007/BF0109 9821

[3] Dong Y., Chawla N., and Swami A., “Metapath2vec: Scalable Representation Learning for Heterogeneous Networks,” in Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, pp. 135-144, 2017. https://doi.org/10.1145/3097983.3098036

[4] Feng M., Heffernan N., and Koedinger K., “Addressing the Assessment Challenge with an Online System that Tutors as it Assesses,” User Modeling and User-Adapted Interaction, vol. 19, pp. 243-266, 2009. https://link.springer.com/article/10.1007/s11257- 009-9063-7

[5] Ghosh A., Heffernan N., and Lan A., “Context- Aware Attentive Knowledge Tracing,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, California, pp. 2330- 2339, 2020. https://doi.org/10.1145/3394486.3403282

[6] Hamilton W., Ying Z., and Leskovec J., “Inductive 246 The International Arab Journal of Information Technology, Vol. 22, No. 2, March 2025 Representation Learning on Large Graphs,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, California, pp. 1025-1035, 2017. https://dl.acm.org/doi/10.5555/3294771.3294869

[7] Koedinger K., Baker R., Cunningham K., Skogsholm A., Leber B., and Stamper J., Handbook of Educational Data Mining, CRC Press, 2010. DOI:10.1201/b10274-6

[8] Le C., Pardos Z., Meyer S., and Thorp R., “Communication at Scale in a MOOC Using Predictive Engagement Analytics,” in Proceedings of the 19th International Conference on Artificial Intelligence in Education, London, pp. 239-252, 2018. https://link.springer.com/chapter/10.1007/978-3- 319-93843-1_18

[9] Li G. and Wang F., “Image Object and Scene Recognition Based on Improved Convolutional Neural Network,” The International Arab Journal of Information Technology, vol. 21, no. 5, pp. 925- 937, 2024. https://doi.org/10.34028/iajit/21/5/13

[10] Liu Y., Yang Y., Chen X., Shen J., Zhang H., and Yu Y., “Improving Knowledge Tracing via Pre- Training Question Embeddings,” in Proceedings of the 29th International Joint Conference on Artificial Intelligence, Yokohama, pp. 1577-1583, 2020. https://www.ijcai.org/proceedings/2020/0219.pdf

[11] Liu Z., Huang C., Yu Y., Fan B., and Dong J., “Fast Attributed Multiplex Heterogeneous Network Embedding,” in Proceedings of the 29th ACM International Conference on Information and Knowledge Management, Ireland, pp. 995-1004, 2020. https://doi.org/10.1145/3340531.3411944

[12] Luo R., Liu F., Liang W., Zhang Y., Bu C., and Hu X., “DAGKT: Difficulty and Attempts Boosted Graph-based Knowledge Tracing,” in Proceedings of the 29th International Conference on Neural Information Processing, New Delhi, pp. 255-266, 2022. https://doi.org/10.1007/978-3- 031-30108-7_22

[13] Nakagawa H., Iwasawa Y., and Matsuo Y., “Graph -based Knowledge Tracing: Modeling Student Proficiency Using Graph Neural Network,” in Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence, Thessaloniki, pp. 156-163, 2019. https://doi.org/10.1145/3350546.3352513

[14] Pandey S. and Karypis G., “A Self-Attentive Model for Knowledge Tracing,” in Proceedings of the 12th International Conference on Educational Data Mining, Montreal, pp. 384-389, 2019. https://drive.google.com/file/d/1yyfa9sWlVRHA Y4JEQyRFZH0lge_p2HGA/view

[15] Patikorn T., Heffernan N., and Baker R., “Assistments Longitudinal Data Mining Competition 2017: A Preface,” in Proceedings of the Workshop on Scientific Findings from the ASSISTments Longitudinal Data Competition during the 11th Conference of Educational Data Mining, Buffalo, pp. 1-11, 2018. https://sites.google.com/view/assistmentsdatamin ing/data-mining-competition-2017

[16] Piech C., Bassen J., Huang J., Ganguli S., Sahami M., Guibas L., and Sohl-Dickstein J., Advances in Neural Information Processing Systems, Curran Associates, 2015. https://papers.nips.cc/paper_files/paper/2015/has h/bac9162b47c56fc8a4d2a519803d51b3- Abstract.html

[17] Song X., Li J., Lei Q., Zhao W., Chen Y., and Mian A., “Bi-CLKT: Bi-Graph Contrastive Learning Based Knowledge Tracing,” Knowledge-Based Systems, vol. 241, pp. 108274, 2022. https://doi.org/10.1016/j.knosys.2022.108274

[18] Velickovic P., Cucurull G., Casanova A., Romero A., Lio P., and Bengio Y., “Graph Attention Networks,” arXiv Preprint, vol. arXiv:1710.10903, pp. 1-12, 2017. https://arxiv.org/abs/1710.10903

[19] Wang X., Ji H., Shi C., Wang B., Ye Y., Cui P., and Yu P., “Heterogeneous Graph Attention Network,” in Proceedings of the World Wide Web Conference, San Francisco, pp. 2022-2032, 2019. https://doi.org/10.1145/3308558.3313562

[20] Williams R. and Zipser D., “A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,” Neural Computation, vol. 1, no. 2, pp. 270-280, 1989. DOI:10.1162/neco.1989.1.2.270

[21] Wu T. and Ling Q., “Fusing Hybrid Attentive Network with Self-Supervised Dual-Channel Heterogeneous Graph for Knowledge Tracing,” Expert Systems with Applications, vol. 225, pp. 120212, 2023. https://doi.org/10.1016/j.eswa.2023.120212

[22] Xu J., Huang X., Xiao T., and Lv P., “Improving Knowledge Tracing via a Heterogeneous Information Network Enhanced by Student Interactions,” Expert Systems with Applications, vol. 232, pp. 120853, 2023. https://doi.org/10.1016/j.eswa.2023.120853

[23] Yang Y., Shen J., Qu Y., Liu Y., Wang K., Zhu Y., Zhang W., and Yu Y., “GIKT: A Graph-based Interaction Model for Knowledge Tracing,” in Proceedings of the Machine Learning and Knowledge Discovery in Databases: European Conference, Ghent, pp. 299-315, 2021. https://doi.org/10.1007/978-3-030-67658-2_18

[24] Yu P., Fu C., Yu Y., Huang C., Zhao Z., and Dong J., “Multiplex Heterogeneous Graph Convolutional Network,” in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington (DC), pp. 2377-2387, 2022. https://doi.org/10.1145/3534678.3539482 Integrating Multiplex Heterogeneous Network for Knowledge Tracing 247

[25] Zhang C., Song D., Huang C., Swami A., and Chawla N., “Heterogeneous Graph Neural Network,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, pp. 793- 803, 2019. https://doi.org/10.1145/3292500.3330961

[26] Zhang J., Shi X., King I., and Yeung D., “Dynamic Key-Value Memory Networks for Knowledge Tracing,” in Proceedings of the 26th International Conference on World Wide Web, Perth, pp. 765- 774, 2017. https://doi.org/10.1145/3038912.3052580

[27] Zhao J., Wang X., Shi C., Hu B., Song G., and Ye Y., “Heterogeneous Graph Structure Learning for Graph Neural Networks,” in Proceedings of the 35th AAAI Conference on Artificial Intelligence, Virtual, pp. 4697-4705, 2021. https://doi.org/10.1609/aaai.v35i5.16600