您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (1): 100-108.doi: 10.6040/j.issn.1672-3961.0.2023.143

• 机器学习与数据挖掘 • 上一篇    

基于交互序列特征相关性的可解释知识追踪

陈成1,董永权1,2,3*,贾瑞1,刘源1   

  1. 1.江苏师范大学计算机科学与技术学院, 江苏 徐州 221116;2.江苏省教育信息化工程技术研究中心, 江苏 徐州 221116;3.徐州市云计算工程技术研究中心, 江苏 徐州 221116
  • 发布日期:2024-02-01
  • 作者简介:陈成(1999— ),男,江苏南京人,硕士研究生,主要研究方向为知识追踪、可解释性. E-mail:15850526434@163.com. *通信作者简介:董永权(1979— ),男,江苏宿迁人,教授,硕士生导师,博士,主要研究方向为数据集成、数据挖掘、群体智能、教育信息化. E-mail:tomdyq@jsnu.edu.cn.
  • 基金资助:
    国家自然科学基金资助项目(61872168);江苏省教育科学十四五规划资助项目(d/2021/01/112);江苏师范大学研究生科研与实践创新计划资助项目(2022XKT1527)

Interpretable knowledge tracing based on the feature relevance of interaction sequence

CHEN Cheng1, DONG Yongquan1,2,3* , JIA Rui1, LIU Yuan1   

  1. 1. School of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, Jiangsu, China;
    2. Jiangsu Educational Informatization Engineering Technology Research Center, Xuzhou 221116, Jiangsu, China;
    3. Xuzhou Cloud Computing Engineering Technology Research Center, Xuzhou 221116, Jiangsu, China
  • Published:2024-02-01

PDF (PC)

57

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
[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.
[1] 卞小曼,王小琴,蓝如师,刘振丙,罗笑南. 基于相似性保持和判别性分析的快速视频哈希算法[J]. 山东大学学报 (工学版), 2023, 53(6): 63-69.
[2] 李鸿钊,张庆松,刘人太,陈新,辛勤,石乐乐. 浅埋地铁车站施工期地表变形风险预警[J]. 山东大学学报 (工学版), 2023, 53(6): 82-91.
[3] 王旭晴,魏伟波,杨光宇,宋金涛,吕婷,潘振宽. 基于算法展开的图像盲去模糊深度学习网络[J]. 山东大学学报 (工学版), 2023, 53(6): 35-46.
[4] 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.
[5] 王碧瑶,韩毅,崔航滨,刘毅超,任铭然,高维勇,陈姝廷,刘嘉巍,崔洋. 基于图像的道路语义分割检测方法[J]. 山东大学学报 (工学版), 2023, 53(5): 37-47.
[6] 周晓昕,廖祝华,刘毅志,赵肄江,方艺洁. 融合历史与当前交通流量的信号控制方法[J]. 山东大学学报 (工学版), 2023, 53(4): 48-55.
[7] 于畅,伍星,邓秋菊. 基于深度学习的多视角螺钉缺失智能检测算法[J]. 山东大学学报 (工学版), 2023, 53(4): 104-112.
[8] 宋佳芮,陈艳平,王凯,黄瑞章,秦永彬. 基于Affix-Attention的命名实体识别语义补充方法[J]. 山东大学学报 (工学版), 2023, 53(2): 70-76.
[9] 袁钺,王艳丽,刘勘. 基于空洞卷积块架构的命名实体识别模型[J]. 山东大学学报 (工学版), 2022, 52(6): 105-114.
[10] 李旭涛,杨寒玉,卢业飞,张玮. 基于深度学习的遥感图像道路分割[J]. 山东大学学报 (工学版), 2022, 52(6): 139-145.
[11] 孟令灿,聂秀山,张雪. 基于遮挡目标去除的公交车拥挤度分类算法[J]. 山东大学学报 (工学版), 2022, 52(4): 83-88.
[12] 袁高腾,周晓峰,郭宏乐. 基于特征选择算法的ECG信号分类[J]. 山东大学学报 (工学版), 2022, 52(4): 38-44.
[13] 杨霄,袭肖明,李维翠,杨璐. 基于层次化双重注意力网络的乳腺多模态图像分类[J]. 山东大学学报 (工学版), 2022, 52(3): 34-41.
[14] 王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[15] 聂秀山,马玉玲,乔慧妍,郭杰,崔超然,于志云,刘兴波,尹义龙. 任务粒度视角下的学生成绩预测研究综述[J]. 山东大学学报 (工学版), 2022, 52(2): 1-14.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发