基于交互序列特征相关性的可解释知识追踪

doi:10.6040/j.issn.1672-3961.0.2023.143

摘要/Abstract

摘要： 为提高知识追踪(knowledge tracing, KT)模型的可解释性,提出适用于KT事后可解释性的Shapley Value和ISP算法以及可解释性评价指标和谐度,以KT领域经典的深度学习模型DKT为例,计算历史交互与预测结果之间的相关性分数,解释DKT的预测结果。Shapley Value算法计算每次交互对预测结果的贡献,将贡献视为相关性分数;ISP算法基于原序列和模型自身的推理能力构造伪标签,实现对原序列的扰动,计算相关性分数;基于解释方法计算出的相关性分数,使用和谐度指标评价各方法的解释效果。在试验层面,5个公开数据集上的试验结果表明,相对于最优的基线方法,本研究提出的方法取得显著的可解释性效果提升;在具体应用层面,利用可解释性挖掘知识点之间的偏序关系,帮助学生探究更加合理的学习顺序。

关键词: 机器学习, 深度学习, 知识追踪, 可解释性, 特征相关性

中图分类号:

TP391

陈成,董永权,贾瑞,刘源. 基于交互序列特征相关性的可解释知识追踪[J]. 山东大学学报 (工学版), 2024, 54(1): 100-108.

CHEN Cheng, DONG Yongquan, JIA Rui, LIU Yuan. Interpretable knowledge tracing based on the feature relevance of interaction sequence[J]. Journal of Shandong University(Engineering Science), 2024, 54(1): 100-108.

参考文献

[1] LIU Tieyuan, CHEN Wei, CHANG Liang, et al. Research advances in the knowledge tracing based on deep learning[J]. Journal of Computer Research and Development, 2022, 59(1): 81-104.
[2] CORBETT A T, ANDERSON J R. Knowledge tracing: modeling the acquisition of procedural knowledge[J]. User Modeling and User-Adapted Interaction, 1994, 4(4): 253-278.
[3] KÄSER T, KLINGLER S, SCHWING A G, et al. Dynamic bayesian networks for student modeling[J]. IEEE Transactions on Learning Technologies, 2017, 10(4): 450-462.
[4] BAKER R S J D., CORBETT A T, ALEVEN V. More accurate student modeling through contextual estimation of slip and guess probabilities in bayesian knowledge tracing[C] //Intelligent Tutoring Systems. Berlin, Germany: Springer, 2008: 406-415.
[5] PARDOS Z A, HEFFERNAN N T. KT-idem: introducing item difficulty to the knowledge tracing model[C] //User Modeling, Adaption and Personalization. Berlin, Germany: Springer, 2011: 243-254.
[6] PIECH C, BASSEN J, HUANG J, et al. Deep knowledge tracing[J]. Advances in Neural Information Processing Systems, 2015, 28: 505-513.
[7] MINN S, YU Y, DESMARAIS M C, et al. Deep knowledge tracing and dynamic student classification for knowledge tracing[C] //2018 IEEE International Conference on Data Mining(ICDM). Singapore: IEEE, 2018: 1182-1187.
[8] YEUNG Chun-Kit, YEUNG Dit-Yan. Addressing two problems in deep knowledge tracing via prediction-consistent regularization[C] //Proceedings of the Fifth Annual ACM Conference on Learning at Scale. London, United Kingdom: Association for Computing Machinery, 2018: 1-10.
[9] 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. New York, USA: Association for Computing Machinery, 2020: 2330-2339.
[10] PANDEY S, KARYPIS G. A self-attentive model for knowledge tracing[EB/OL].(2019-07-16)[2022-02-21]. http://arxiv.org/abs/1907.06837.
[11] CHOI Y, LEE Y, CHO J, et al. Towards an appropriate query, key, and value computation for knowledge tracing[C] //Proceedings of the Seventh ACM Conference on Learning @ Scale. New York, USA: Association for Computing Machinery, 2020: 341-344.
[12] ZHOU Y, LI X, CAO Y, et al. LANA: towards personalized deep knowledge tracing through distinguishable interactive sequences[EB/OL].(2021-04-20)[2023-03-20]. http://arxiv.org/abs/2105.06266.
[13] WU Z, HUANG L, HUANG Q, et al. SGKT: session graph-based knowledge tracing for student performance prediction[J]. Expert Systems with Applications, 2022, 206: 117681.
[14] LIU S, YU J, LI Q, et al. Ability boosted knowledge tracing[J]. Information Sciences, 2022, 596: 567-587.
[15] SIMONYAN K, VEDALDI A, ZISSERMAN A. Deep inside convolutional networks: visualising image classification models and saliency maps[EB/OL].(2014-04-19)[2023-02-13]. http://arxiv.org/abs/1312.6034.
[16] LI J, MONROE W, JURAFSKY D. Understanding neural networks through representation erasure[EB/OL].(2017-01-09)[2023-02-13]. http://arxiv.org/abs/1506.06579.
[17] FONG R C, VEDALDI A. Interpretable explanations of black boxes by meaningful perturbation[C] //2017 IEEE International Conference on Computer Vision(ICCV). New York, USA: [S.l.] , 2017: 3429-3437.
[18] KOH P W, LIANG P. Understanding black-box predictions via influence functions[C] //International Conference on Machine Learning. Sydney, Australia: PMLR, 2017: 1885-1894.
[19] ZHANG H, XIE Y, ZHENG L, et al. Interpreting multivariate shapley interactions in dnns[C] //Proceedings of the AAAI Conference on Artificial Intelligence. Menlo Park, USA: AAAI Press, 2021: 10877-10886.
[20] WICH M, MOSCA E, GORNIAK A, et al. Explainable abusive language classification leveraging user and network data[C] //Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2021: 481-496.
[21] MA H, ZHANG H, ZHOU F, et al. Quantification and analysis of layer-wise and pixel-wise information discarding[C] //Proceedings of the 39th International Conference on Machine Learning. Sydney, Australia: PMLR, 2022: 14664-14698.
[22] LU Y, WANG D, MENG Q, et al. Towards interpretable deep learning models for knowledge tracing[C] //Artificial Intelligence in Education. Berlin, Germany: Springer, 2020: 185-190.
[23] BACH S, BINDER A, MONTAVON G, et al. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation[J]. PLOS ONE, 2015, 10(7): 0130140.
[24] DING X, LARSON E C. Why deep knowledge tracing has less depth than anticipated[C] //Proceedings of the 12th International Conference on Educational Data Mining. Montreal, Canada: ERIC, 2019: 282-287.
[25] DING X, LARSON E C. Incorporating uncertainties in student response modeling by loss function regularization[J]. Neurocomputing, 2020, 409: 74-82.
[26] HU Q, RANGWALA H. Reliable deep grade prediction with uncertainty estimation[C] //Proceedings of the 9th International Conference on Learning Analytics & Knowledge. New York, USA: Association for Computing Machinery, 2019: 76-85.
[27] GUHA R, KHAN A H, SINGH P K, et al. CGA: a new feature selection model for visual human action recognition[J]. Neural Computing and Applications, 2021, 33(10): 5267-5286.
[28] GHORBANI A, ZOU J Y. Neuron shapley: discovering the responsible neurons[J]. Advances in Neural Information Processing Systems, 2020, 33: 5922-5932.
[29] GABRIELLA C, GRILLI L, LIMONE P, et al. Deep learning for knowledge tracing in learning analytics: an overview[C] //CEUR Workshop Proceedings. Foggia, Italy: CEUR-WS, 2021: 1-10.
[30] ROZEMBERCZKI B, WATSON L, BAYER P, et al. The shapley value in machine learning[EB/OL].(2022-05-26)[2023-03-20]. http://arxiv.org/abs/2202.05594.

相关文章 15

[1]	李常刚,李宝亮,曹永吉,王佳颖. 人工智能在电力系统潮流计算中的应用综述及展望[J]. 山东大学学报 (工学版), 2025, 55(5): 1-17.
[2]	周群颖,隋家成,张继,王洪元. 基于自监督卷积和无参数注意力机制的工业品表面缺陷检测[J]. 山东大学学报 (工学版), 2025, 55(4): 40-47.
[3]	薛冰冰,王勇,杨维浩,王川,于迪,王旭. 基于ETC收费数据的高速公路交通流数据修复及实时预测[J]. 山东大学学报 (工学版), 2025, 55(3): 58-71.
[4]	董明书,陈俐企,马川义,张珠皓,孙仁娟,管延华,庄培芝. 沥青路面内部裂缝雷达图像智能判识算法研究[J]. 山东大学学报 (工学版), 2025, 55(3): 72-79.
[5]	祝明,石承龙,吕潘,刘现荣,孙驰,陈建城,范宏运. 基于优化长短时记忆网络的深基坑变形预测方法及其工程应用[J]. 山东大学学报 (工学版), 2025, 55(3): 141-148.
[6]	常新功,苏敏惠,周志刚. 基于进化集成的图神经网络解释方法[J]. 山东大学学报 (工学版), 2024, 54(4): 1-12.
[7]	乔慧妍,段学龙,解驰皓,赵冬慧,马玉玲. 基于异常点检测的心理健康辅助诊断方法[J]. 山东大学学报 (工学版), 2024, 54(4): 76-85.
[8]	索大翔,李波. 基于Gromov-Wasserstein最优传输的输电线路小目标检测方法[J]. 山东大学学报 (工学版), 2024, 54(3): 22-29.
[9]	宋辉,张轶哲,张功萱,孟元. 基于类权重和最小化预测熵的测试时集成方法[J]. 山东大学学报 (工学版), 2024, 54(3): 36-43.
[10]	刘新,刘冬兰,付婷,王勇,常英贤,姚洪磊,罗昕,王睿,张昊. 基于联邦学习的时间序列预测算法[J]. 山东大学学报 (工学版), 2024, 54(3): 55-63.
[11]	岳仁峰,张嘉琦,刘勇,范学忠,李琮琮,孔令鑫. 基于颜色和纹理特征的立体车库锈蚀检测技术[J]. 山东大学学报 (工学版), 2024, 54(3): 64-69.
[12]	聂秀山,巩蕊,董飞,郭杰,马玉玲. 短视频场景分类方法综述[J]. 山东大学学报 (工学版), 2024, 54(3): 1-11.
[13]	李璐,张志军,范钰敏,王星,袁卫华. 面向冷启动用户的元学习与图转移学习序列推荐[J]. 山东大学学报 (工学版), 2024, 54(2): 69-79.
[14]	高泽文,王建,魏本征. 基于混合偏移轴向自注意力机制的脑胶质瘤分割算法[J]. 山东大学学报 (工学版), 2024, 54(2): 80-89.
[15]	李家春,李博文,常建波. 一种高效且轻量的RGB单帧人脸反欺诈模型[J]. 山东大学学报 (工学版), 2023, 53(6): 1-7.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed