Paper Recommendation Based on Academic Knowledge Graph and Subject Feature Embedding
Li Kaijun1,Niu Zhendong1(),Shi Kaize1,2,Qiu Ping1
1School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China 2Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney 2007, Australia
[Objective] This paper proposes a new model that integrates multiple features to provide accurate paper recommendation services for researchers. [Methods] First, we designed a feature extraction framework to extract and fuse entity relation features and topic features from the knowledge graph and the content of academic papers, respectively. Then, we proposed a paper recommendation method based on the knowledge embedding-based encoding-decoding model, which improved the learning effect of high-dimensional fusion features. [Results] We examined our new model on the DBLP-v11 dataset. The proposed method improved the Recall and MRR scores by 8.9% and 2.9%, respectively, compared with the suboptimal model. [Limitations] The proposed graph feature learning method does not consider the weight of entities in the real environment. [Conclusions] The new paper recommendation method could effectively learn high-dimensional features, which provide guidance for subsequent research.
李锴君, 牛振东, 时恺泽, 邱萍. 基于学术知识图谱及主题特征嵌入的论文推荐方法*[J]. 数据分析与知识发现, 2023, 7(5): 48-59.
Li Kaijun, Niu Zhendong, Shi Kaize, Qiu Ping. Paper Recommendation Based on Academic Knowledge Graph and Subject Feature Embedding. Data Analysis and Knowledge Discovery, 2023, 7(5): 48-59.
Remote Policy Enforcement ···Execution in Mobile Environments
作者信息
作者ID、姓名以及隶属工作机构
出版机构
出版机构 ID 以及名称
年份
2013
参考论文
本篇论文引用的论文 ID 组成的列表
摘要
Both in ···viableand effective.
Table 3 数据集元数据
Top N
KE-EDM (本文)
HKE-ARNN
Citeomatic
ClusCite
VOPRec
查准率
查全率
F1 分数
查准率
查全率
F1 分数
查准率
查全率
F1 分数
查准率
查全率
F1 分数
查准率
查全率
F1 分数
1
0.686
0.337
0.452
0.654
0.062
0.113
0.469
0.039
0.072
0.412
0.019
0.036
0.313
0.053
0.091
5
0.516
0.406
0.454
0.511
0.162
0.246
0.348
0.140
0.200
0.352
0.152
0.212
0.187
0.160
0.172
10
0.265
0.463
0.337
0.281
0.291
0.286
0.294
0.235
0.261
0.242
0.212
0.226
0.159
0.280
0.203
20
0.150
0.682
0.247
0.160
0.593
0.252
0.222
0.354
0.273
0.195
0.300
0.236
0.135
0.410
0.203
50
0.064
0.705
0.117
0.067
0.596
0.120
0.139
0.539
0.221
0.111
0.427
0.176
0.059
0.460
0.105
Table 4 KE-EDM模型与基线模型的性能
Fig.2 各模型的MRR分数
主题特征
Precision@20
Recall@20
F1分数
MRR
标题&摘要
0.151
0.682
0.247
0.687
标题
0.150
0.655
0.244
0.659
摘要
0.151
0.662
0.245
0.686
Table 5 不同主题特征的嵌入对模型性能的影响分析
Fig.3 不同维度的向量特征对模型推荐性能的影响
方法
Precision@20
Recall@20
F1分数
MRR
TransD
0.151
0.682
0.247
0.687
TransR
0.150
0.675
0.245
0.689
TransH
0.146
0.664
0.239
0.656
TransE
0.144
0.650
0.235
0.649
Table 6 不同图谱特征表示学习方法对模型性能的影响分析
[1]
Liu X Z, Yu Y Y, Guo C, et al. Meta-Path-Based Ranking with Pseudo Relevance Feedback on Heterogeneous Graph for Citation Recommendation[C]// Proceedings of the 23rd ACM International Conference on Information and Knowledge Management. 2014: 121-130.
[2]
Wu T, Liu Z W, Huang Q Q, et al. Adversarial Robustness under Long-Tailed Distribution[C]// Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 8655-8664.
[3]
Beel J, Gipp B, Langer S, et al. Research-Paper Recommender Systems: A Literature Survey[J]. International Journal on Digital Libraries, 2016, 17(4): 305-338.
doi: 10.1007/s00799-015-0156-0
[4]
Zhang Y, Yang L B, Cai X Y, et al. A Novel Personalized Citation Recommendation Approach Based on GAN[C]// Proceedings of International Symposium on Methodologies for Intelligent Systems. 2018: 268-278.
[5]
Goyal P, Ferrara E. Graph Embedding Techniques, Applications, and Performance: A Survey[J]. Knowledge-Based Systems, 2018, 151: 78-94.
doi: 10.1016/j.knosys.2018.03.022
(Huang Lu, Lin Chuanjie, He Jun, et al. Diversified Mobile App Recommendation Combining Topic Model and Collaborative Filtering[J]. Journal of Software, 2017, 28(3): 708-720.)
[7]
Zhu Y F, Lin Q K, Lu H, et al. Recommending Scientific Paper via Heterogeneous Knowledge Embedding Based Attentive Recurrent Neural Networks[J]. Knowledge-Based Systems, 2021, 215: 106744.
doi: 10.1016/j.knosys.2021.106744
[8]
Dai Z H, Yang Z L, Yang Y M, et al. Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017: 6000-6010.
[9]
Vaswani A, Shazeer N, Parmar N, et al. Attention is All You Need[C]// Proceedings of the 31st Conference on Neural Information Processing Systems. 2017.
[10]
Ji G L, He S Z, Xu L H, et al. Knowledge Graph Embedding via Dynamic Mapping Matrix[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1:Long papers). 2015: 687-696.
[11]
Tang T Y, McCalla G. A Multidimensional Paper Recommender: Experiments and Evaluations[J]. IEEE Internet Computing, 2009, 13(4): 34-41.
[12]
Gori M, Pucci A. Research Paper Recommender Systems: A Random-Walk Based Approach[C]// Proceedings of 2006 IEEE/WIC/ACM International Conference on Web Intelligence. 2006: 778-781.
[13]
Beel J, Langer S, Genzmehr M, et al. Research Paper Recommender System Evaluation: A Quantitative Literature Survey[C]// Proceedings of the International Workshop on Reproducibility and Replication in Recommender Systems Evaluation. 2013: 15-22.
[14]
Ma S T, Zhang C Z, Liu X Z. A Review of Citation Recommendation: From Textual Content to Enriched Context[J]. Scientometrics, 2020, 122(3): 1445-1472.
doi: 10.1007/s11192-019-03336-0
[15]
Yang L B, Zheng Y, Cai X Y, et al. A LSTM Based Model for Personalized Context-Aware Citation Recommendation[J]. IEEE Access, 2018, 6: 59618-59627.
doi: 10.1109/ACCESS.2018.2872730
[16]
Nascimento C, Laender A H F, da Silva A S, et al. A Source Independent Framework for Research Paper Recommendation[C]// Proceedings of the 11th Annual International ACM/IEEE Joint Conference on Digital Libraries. 2011: 297-306.
[17]
Amami M, Pasi G, Stella F, et al. An LDA-Based Approach to Scientific Paper Recommendation[C]// Proceedings of International Conference on Applications of Natural Language to Information Systems. 2016: 200-210.
[18]
Achakulvisut T, Acuna D E, Ruangrong T, et al. Science Concierge: A Fast Content-Based Recommendation System for Scientific Publications[J]. PLoS One, 2016, 11(7): e0158423.
doi: 10.1371/journal.pone.0158423
[19]
Bhagavatula C, Feldman S, Power R, et al. Content-Based Citation Recommendation[C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, Volume 1 (Long Papers). 2018: 238-251.
[20]
Beel J, Langer S, Genzmehr M, et al. Introducing Docear′s Research Paper Recommender System[C]// Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries. 2013: 459-460.
[21]
Gazdar A, Hidri L. A New Similarity Measure for Collaborative Filtering Based Recommender Systems[J]. Knowledge-Based Systems, 2020, 188: 105058.
doi: 10.1016/j.knosys.2019.105058
[22]
Wang C, Blei D M. Collaborative Topic Modeling for Recommending Scientific Articles[C]// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2011: 448-456.
[23]
Bansal T, Belanger D, McCallum A. Ask the GRU: Multi-task Learning for Deep Text Recommendations[C]// Proceedings of the 10th ACM Conference on Recommender Systems. 2016: 107-114.
[24]
Sugiyama K, Kan M Y. Exploiting Potential Citation Papers in Scholarly Paper Recommendation[C]// Proceedings of the 13th ACM/IEEE-CS Joint Conference on Digital Libraries. 2013: 153-162.
[25]
Son J, Kim S B. Academic Paper Recommender System Using Multilevel Simultaneous Citation Networks[J]. Decision Support Systems, 2018, 105: 24-33.
doi: 10.1016/j.dss.2017.10.011
[26]
Lops P, Gemmis M, Semeraro G. Content-Based Recommender Systems:State of the Art and Trends[A]// Recommender Systems Handbook[M]. Cham: Springer, 2011: 73-105.
[27]
Ali Z, Qi G L, Kefalas P, et al. A Graph-Based Taxonomy of Citation Recommendation Models[J]. Artificial Intelligence Review, 2020, 53(7): 5217-5260.
doi: 10.1007/s10462-020-09819-4
[28]
Tian G, Jing L P. Recommending Scientific Articles Using Bi-relational Graph-Based Iterative RWR[C]// Proceedings of the 7th ACM Conference on Recommender Systems. 2013: 399-402.
[29]
Chakraborty T, Modani N, Narayanam R, et al. DiSCern: A Diversified Citation Recommendation System for Scientific Queries[C]// Proceedings of 2015 IEEE 31st International Conference on Data Engineering. 2015: 555-566.
[30]
Xia F, Liu H F, Lee I, et al. Scientific Article Recommendation: Exploiting Common Author Relations and Historical Preferences[J]. IEEE Transactions on Big Data, 2016, 2(2): 101-112.
doi: 10.1109/TBDATA.2016.2555318
[31]
Manju G, Abhinaya P, Hemalatha M R, et al. Cold Start Problem Alleviation in A Research Paper Recommendation System Using the Random Walk Approach on A Heterogeneous UserPaper Graph[J]. International Journal of Intelligent Information Technologies, 2020, 16 (2): 24-48.
doi: 10.4018/IJIIT
[32]
Huang W Y, Wu Z H, Liang C, et al. A Neural Probabilistic Model for Context Based Citation Recommendation[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence. 2015, 29: 2404-2410.
[33]
Jiang Z R, Liu X Z, Gao L C. Chronological Citation Recommendation with InformationNeed Shifting[C]// Proceedings of the 24th ACM International Conference on Information and Knowledge Management. 2015: 1291-1300.
[34]
Le Q V, Mikolov T. Distributed Representations of Sentences and Documents[C]// Proceedings of the 31st International Conference on Machine Learning. 2014: 1188-1196.
[35]
Cho K, van Merrienboer B, Gulcehre C, et al. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014: 1724-1734.
[36]
Ren X, Liu J L, Yu X, et al. ClusCite: Effective Citation Recommendation by Information Network-Based Clustering[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014: 821-830.
[37]
Kong X J, Mao M Y, Wang W, et al. VOPRec: Vector Representation Learning of Papers with Text Information and Structural Identity for Recommendation[J]. IEEE Transactions on Emerging Topics in Computing, 2021, 9(1): 226-237.
doi: 10.1109/TETC.6245516