知识图与行为图混合嵌入的学习者偏好预测

doi:10.11959/j.issn.1000-436x.2021125

通信学报 ›› 2021, Vol. 42 ›› Issue (8): 130-138.doi: 10.11959/j.issn.1000-436x.2021125

知识图与行为图混合嵌入的学习者偏好预测

李晓光¹, 宫磊¹, 李晓莉¹, 张昕¹, 于戈²

¹ 辽宁大学信息学院，辽宁沈阳 110036
² 东北大学计算机科学与工程学院，辽宁沈阳 110169

修回日期:2021-03-08 出版日期:2021-08-25 发布日期:2021-08-01
作者简介:李晓光（1973- ），男，辽宁沈阳人，博士，辽宁大学教授、硕士生导师，主要研究方向为机器学习等
宫磊（1996- ），男，辽宁大连人，辽宁大学硕士生，主要研究方向为推荐系统等
李晓莉（1973- ），女，辽宁沈阳人，辽宁大学副教授，主要研究方向为大数据等
张昕（1979- ），男，辽宁沈阳人，博士，辽宁大学副教授、硕士生导师，主要研究方向为复杂系统等
于戈（1962- ），男，辽宁沈阳人，博士，东北大学教授，主要研究方向为数据库等
基金资助:
国家自然科学基金资助项目(U1811261);辽宁省教育厅高等学校基本科研基金资助项目(LWF201705)

Learner preferences prediction with mixture embedding of knowledge and behavior graph

Xiaoguang LI¹, Lei GONG¹, Xiaoli LI¹, Xin ZHANG¹, Ge YU²

¹ School of Information, Liaoning University, Shenyang 110036, China
² School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China

Revised:2021-03-08 Online:2021-08-25 Published:2021-08-01
Supported by:
The National Natural Science Foundation of China(U1811261);Basic Scientific Research Project of Higher Education Institutions of Education Department of Liaoning Province(LWF201705)

摘要/Abstract

摘要：

为了解决知识推荐模型中学习者偏好预测不准确、结构信息利用不充分等问题，针对学习者偏好预测模型中知识结构与学习者行为结构，提出了知识图与行为图混合嵌入的学习者偏好预测模型。首先，考虑使用图卷积的方式拟合结构信息，将图卷积扩展至知识图以及行为图，获取学习者整体性学习规律与个体性学习规律。然后，模型利用知识结构与行为结构的差异性拟合学习者个性化偏好，采用循环神经网络将学习者的过程性偏好进行编码与解码，获得学习者偏好分布。在真实数据集上的实验结果表明，所提模型对拟合学习者偏好效果良好。

关键词: 知识图, 行为图, 图卷积网络, 知识推荐

Abstract:

To solve the problems of inaccurate prediction of learner preference and insufficient utilization of structural information in the knowledge recommendation model, for the knowledge structure and learner behavior structure in the learner’s preference prediction model, the model of learner preferences predication with mixture embedding of knowledge and behavior graph was proposed.First, considering using graph convolution network (GCN) to fit structural information, GCN was extended to knowledge graph and behavior graph, the purpose of which was to obtain learners’ overall learning pattern and individual learning pattern.Then, the difference between knowledge structure and behavior structure was used to fit learners’ individual preferences, and recurrent neural network was used to encode and decode learners’ preferences to obtain the distribution of learners’ preference distribution.The experimental results on the real datasets demonstrate that the proposed model has a good effect on predicting learner preferences.

Key words: knowledge graph, behavior graph, GCN, knowledge recommendation

中图分类号:

TN92

李晓光, 宫磊, 李晓莉, 张昕, 于戈. 知识图与行为图混合嵌入的学习者偏好预测[J]. 通信学报, 2021, 42(8): 130-138.

Xiaoguang LI, Lei GONG, Xiaoli LI, Xin ZHANG, Ge YU. Learner preferences prediction with mixture embedding of knowledge and behavior graph[J]. Journal on Communications, 2021, 42(8): 130-138.

图/表 10

图1

图2

表1

表2

表3

KGBR与基线方法比较结果"

方法	AUC
方法	Algebra1/20	Assitment1/10
MF	0.62	0.63
NFM	0.64	0.65
NGCF	0.69	0.70
RippleNet	0.80	0.82
SR-GNN	0.81	0.82
KGBR	$0 . 83$	$0 . 85$
KGBR_{(withoutRGAT)}	$0 . 76$	$0 . 77$
KGBR_{(withoutKGCN)}	$0 . 80$	$0 . 82$

表3

表4

不同融合方式比较结果"

方法	AUC
方法	Algebra1/20	Assitment1/10
KGBR-avg	0.80	0.81
KGBR-inner	0.81	0.81
KGBR-concat	0.82	0.83
KGBR-DEF	$0 . 83$	$0 . 85$

表4

表5

图3

图4

图5

参考文献 26

[1]	TANISKIDOU E K , PAPADAKIS G , GIANNAKOPOULOS G ,et al. Comparative analysis of content-based personalized microblog recommendations experiments and analysis[J]. arXiv Preprint,arXiv:1901.05497, 2019.
[2]	ZHOU T Q , CHEN L N , SHEN J . Collaborative filtering-based recommendation system for big data[J]. International Journal of Computational Science and Engineering, 2020,21(2): 219.
[3]	CHEN J , WANG X S , ZHAO S ,et al. Deep attention user-based collaborative filtering for recommendation[J]. Neurocomputing, 2020,383: 57-68.
[4]	HE X N , LIAO L Z , ZHANG H W ,et al. Neural collaborative filtering[C]// Proceedings of the 26th International Conference on World Wide Web. New York:ACM Press, 2017: 173-182.
[5]	BOBADILLA J , ORTEGA F , GUTIéRREZ A , ,et al. Classification-based deep neural network architecture for collaborative filtering recommender systems[J]. International Journal of Interactive Multimedia and Artificial Intelligence, 2020,6(1): 68.
[6]	VELICKOVIC P , CUCURULL G , CASANOVA A ,et al. Graph attention networks[J]. arXiv Preprint,arXiv:1710.10903, 2017.
[7]	KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks[J]. arXiv Preprint,arXiv:1609.02907, 2016.
[8]	WU S , TANG Y Y , ZHU Y Q ,et al. Session-based recommendation with graph neural networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019,33: 346-353.
[9]	BERG R V D , KIPF T N , WELLING M . Graph convolutional matrix completion[J]. arXiv Preprint,arXiv:1706.02263, 2017.
[10]	ZHANG M H , CHEN Y X . Inductive matrix completion based on graph neural networks[J]. arXiv Preprint,arXiv:1904.12058, 2019.
[11]	MNIH A , SALAKHUTDINOV R . Probabilistic matrix factorization[C]// Advances in neural information processing systems. Massachusetts:MIT Press, 2007: 1257-1264.
[12]	KOREN Y , BELL R , VOLINSKY C . Matrix factorization techniques for recommender systems[J]. Computer, 2009,42(8): 30-37.
[13]	KOREN Y , BELL R . Advances in collaborative filtering[M]. Berlin: Springer, 2011.
[14]	PANG Y , JIN Y , ZHANG Y ,et al. Collaborative filtering recommendation for MOOC application[J]. Computer Applications in Engineering Education, 2017,25(1): 120-128.
[15]	PANG Y X , LIU W Y , JIN Y Y ,et al. Adaptive recommendation for MOOC with collaborative filtering and time series[J]. Computer Applications in Engineering Education, 2018,26(6): 2071-2083.
[16]	PUJAHARI A , SISODIA D S . Pair-wise preference relation based probabilistic matrix factorization for collaborative filtering in recommender system[J]. Knowledge-Based Systems, 2020,196:105798.
[17]	LI K K , ZHOU X Z , LIN F ,et al. Deep probabilistic matrix factorization framework for online collaborative filtering[J]. IEEE Access, 2019,7: 56117-56128.
[18]	XIAO Y Y , WANG G W , HSU C H ,et al. A time-sensitive persona lized recommendation method based on probabilistic matrix factorization technique[J]. Soft Computing, 2018,22(20): 6785-6796.
[19]	PARDOS Z A , HEFFERNAN N T . Modeling individualization in a Bayesian networks implementation of knowledge tracing[C]// User Modeling,Adaptation,and Personalization. Berlin:Springer, 2010: 255-266.
[20]	ZHANG K , YAO Y Y . A three learning states Bayesian knowledge tracing model[J]. Knowledge-Based Systems, 2018,148: 189-201.
[21]	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. Piscataway:IEEE Press, 2018: 1182-1187.
[22]	WANG X , HE X N , WANG M ,et al. Neural graph collaborative filtering[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2019: 165-174.
[23]	LIAN J X , ZHOU X H , ZHANG F Z ,et al. Combining explicit and implicit feature interactions for recommender systems[J]. arXiv Preprint,arXiv:1803.05170, 2018.
[24]	RENDLE S , FREUDENTHALER C , GANTNER Z ,et al. BPR:Bayesian personalized ranking from implicit feedback[J]. arXiv Preprint,arXiv:1205.2618, 2012.
[25]	HE X N , CHUA T S . Neural factorization machines for sparse predictive analytics[C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2017: 355-364.
[26]	WANG H W , ZHANG F Z , WANG J L ,et al. RippleNet:propagating user preferences on the knowledge graph for recommender systems[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York:ACM Press, 2018: 417-426.

数据集	知识点数/个	试题数/个	记录数/个	学生数/个
Algebra1/20	240	1 843	53 427	575
Assitment1/10	113	13 409	46 298	287

数据集	KGCN	RGAT	DEF	编码器	解码器
Algebra 1/20	1×240	1×480	480×1	240×240	240×240
Assitment 1/10	1×113	1×226	226×1	113×113	113×113

知识图与行为图混合嵌入的学习者偏好预测

Learner preferences prediction with mixture embedding of knowledge and behavior graph

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 26

相关文章 5

Metrics

推荐阅读 0

隐藏层	AUC
隐藏层	Algebra1/20	Assitment1/10
MLP-0	0.63	0.66
MLP-1	0.82	0.83
MLP-2	0.83	0.85
MLP-3	0.81	0.83

[1]	李荣鹏, 汪丙炎, 张宏纲, 赵志峰. 知识增强的语义通信接收端设计[J]. 通信学报, 2023, 44(6): 70-76.
[2]	徐泽汐, 庄雷, 张坤丽, 桂明宇. 基于知识图谱的服务功能链在线部署算法[J]. 通信学报, 2022, 43(8): 41-51.
[3]	孙佳琛, 王金龙, 丁国如, 陈瑾, 龚玉萍. 频谱知识图谱：面向未来频谱管理的智能引擎[J]. 通信学报, 2021, 42(5): 1-12.
[4]	赵晓娟, 贾焰, 李爱平, 陈恺. 基于层级注意力机制的链接预测模型研究[J]. 通信学报, 2021, 42(3): 36-44.
[5]	王晓阳,郑骁庆,肖仰华. 智慧搜索中的实体与关联关系建模与挖掘[J]. 通信学报, 2015, 36(12): 178-189.