Citation recommendation algorithm fusing knowledge graph and graph attention network

doi:10.11772/j.issn.1001-9081.2022071110

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (8): 2420-2425.DOI: 10.11772/j.issn.1001-9081.2022071110

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Citation recommendation algorithm fusing knowledge graph and graph attention network

Haiwei FAN, Xinsiyu LU(), Limiao ZHANG, Yisheng AN

School of Information Engineering，Chang’an University，Xi’an Shaanxi 710064，China

Received:2022-07-29 Revised:2022-11-20 Accepted:2022-11-30 Online:2023-01-15 Published:2023-08-10
Contact: Xinsiyu LU
About author:FAN Haiwei， born in 1974， M. S.， associate professor. His research interests include software system design， machine learning.
ZHANG Limiao， born in 1997， M. S. candidate. Her research interests include deep learning.
AN Yisheng， born in 1972， Ph. D.， professor. His research interests include computer-support collaborative design， Petri network.
Supported by:
Shaanxi Higher Education and Teaching Reform Research Project(21BY031);the Second Batch of New Engineering Research and Practice Project in Shaanxi Province （54）, Fundamental Research Funds for the Central Universities(300103112403)

融合知识图谱和图注意力网络的引文推荐算法

樊海玮, 鲁芯丝雨(), 张丽苗, 安毅生

长安大学信息工程学院，西安 710064

通讯作者: 鲁芯丝雨
作者简介:樊海玮（1974—），男，陕西西安人，副教授，硕士，主要研究方向：软件系统设计、机器学习
张丽苗（1997—），女，山西临汾人，硕士研究生，主要研究方向：深度学习
安毅生（1972—），男（回族），陕西西安人，教授，博士，主要研究方向：计算机支持协同设计、Petri网。
基金资助:
陕西高等教育教学改革研究项目(21BY031);陕西省第二批新工科研究与实践项目(54);中央高校基本科研业务费专项(300103112403)

Abstract

Abstract:

Aiming at problems of data sparseness and cold start in traditional Collaborative Filtering （CF） and problem that meta-path and random walk algorithms do not fully utilize node information， a Citation Recommendation Algorithm Fusing Knowledge Graph and Graph Attention Network （C-KGAT） was proposed. Firstly， knowledge graph information was mapped into low-dimensional dense vectors by using TransR algorithm to obtain embedded feature representation of the nodes. Secondly， through multi-channel fusion mechanism， graph attention network was used to aggregate neighbor node information to enrich semantics of target nodes and capture high-order connectivity between nodes. Thirdly， without affecting depth or width of network， dynamic convolutional layer was introduced to aggregate information of neighbor nodes dynamically to improve expression ability of the model. Finally， the interaction probabilities of users and citations were calculated through the prediction layer. Experimental results on public datasets AAN （ACL Anthology Network） and DataBase systems and Logic Programming （DBLP） show that the proposed algorithm performs better than all comparison models. The MRR （Mean Reciprocal Rank） of the proposed algorithm is increased by 6.0 and 3.4 percentage points respectively compared with that of the suboptimal model NNSelect， and the $P r e c i s i o n$ and $R e c a l l$ indicators of the proposed algorithm also have different degrees of improvement， which verifies the effectiveness of the algorithm.

Key words: knowledge graph, graph attention network, citation recommendation, dynamic convolution, aggregation

摘要：

针对传统协同过滤（CF）中的数据稀疏和冷启动问题，以及元路径、随机游走算法没有充分利用节点信息的问题，提出融合知识图谱和图注意力网络的引文推荐算法（C-KGAT）。首先，使用TransR算法将知识图谱信息映射为低维稠密向量，以获取节点的嵌入特征表示；其次，利用图注意力网络通过多通道融合机制聚合邻居节点信息以丰富目标节点的语义，并捕获节点间高阶连通性；接着，在不影响网络的深度或宽度的情况下，引入动态卷积层动态地聚合邻居节点信息以提升模型的表达能力；最后，通过预测层计算用户和引文的交互概率。在公开数据集AAN（ACL Anthology Network）和计算机科学文献库（DBLP）上的实验结果表明，所提算法的效果优于所有对比模型，所提算法的MRR（Mean Reciprocal Rank）相较于次优模型NNSelect分别提升了6.0和3.4个百分点，所提算法的精确率和召回率指标也有不同程度的提升，验证了算法的有效性。

关键词: 知识图谱, 图注意力网络, 引文推荐, 动态卷积, 聚合

CLC Number:

TP391.3

Haiwei FAN, Xinsiyu LU, Limiao ZHANG, Yisheng AN. Citation recommendation algorithm fusing knowledge graph and graph attention network[J]. Journal of Computer Applications, 2023, 43(8): 2420-2425.

樊海玮, 鲁芯丝雨, 张丽苗, 安毅生. 融合知识图谱和图注意力网络的引文推荐算法[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2420-2425.

Figures/Tables 9

References 25

1	GAZDAR A， HIDRI L. A new similarity measure for collaborative filtering based recommender systems［J］. Knowledge-Based Systems， 2020， 188： No.105058. 10.1016/j.knosys.2019.105058
2	ALI Z， ULLAH I， KHAN A， et al. An overview and evaluation of citation recommendation models［J］. Scientometrics， 2021， 126（5）： 4083-4119. 10.1007/s11192-021-03909-y
3	ALFARHOOD M， CHENG J L. CATA++： a collaborative dual attentive autoencoder method for recommending scientific articles［J］. IEEE Access， 2020， 8： 183633-183648. 10.1109/access.2020.3029722
4	ALI Z， QI G L， MUHAMMAD K， et al. Paper recommendation based on heterogeneous network embedding［J］. Knowledge-Based Systems， 2020， 210： No.106438. 10.1016/j.knosys.2020.106438
5	YANG L B， ZHANG Z Q， CAI X Y， et al. Attention-based personalized encoder-decoder model for local citation recommendation［J］. Computational Intelligence and Neuroscience， 2019， 2019： No.1232581. 10.1155/2019/1232581
6	DAI T， ZHU L， WANG Y X， et al. Attentive stacked denoising autoencoder with Bi-LSTM for personalized context-aware citation recommendation［J］. IEEE/ACM Transactions on Audio， Speech， and Language Processing， 2020， 28： 553-568. 10.1109/taslp.2019.2949925
7	ALI Z， KEFALAS P， MUHAMMAD K， et al. Deep learning in citation recommendation models survey［J］. Expert Systems with Applications， 2020， 162： No.113790. 10.1016/j.eswa.2020.113790
8	CAI X Y， ZHENG Y， YANG L B， et al. Bibliographic network representation based personalized citation recommendation［J］. IEEE Access， 2019， 7： 457-467. 10.1109/access.2018.2885507
9	ZHANG Y， MA Q. Citation recommendations considering content and structural context embedding［C］// Proceedings of 2020 IEEE International Conference on Big Data and Smart Computing. Piscataway： IEEE， 2020： 1-7. 10.1109/bigcomp48618.2020.0-109
10	ZHOU J， CUI G Q， HU S D， et al. Graph neural networks： a review of methods and applications［J］. AI Open， 2020， 1： 57-81. 10.1016/j.aiopen.2021.01.001
11	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. 10.1007/s11192-019-03336-0
12	YIN J， LI X M. Personalized citation recommendation via convolutional neural networks［C］// Proceedings of 2017 Asia-Pacific Web and Web-Age Information Management Joint Conference on Web and Big Data， LNCS 10367. Cham： Springer， 2017： 285-293.
13	DU Z X， TANG J， DING Y H. POLAR： attention-based CNN for one-shot personalized article recommendation［C］// Proceedings of 2018 Joint European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS 11052. Cham： Springer， 2019： 675-690.
14	ZHANG Z L， LI Z F， LIU H， et al. Multi-scale dynamic convolutional network for knowledge graph embedding［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（5）： 2335-2347. 10.1109/tkde.2020.3005952
15	DING E J， CHENG Y H， XIAO C C， et al. Efficient attention mechanism for dynamic convolution in lightweight neural network［J］. Applied Sciences， 2021， 11（7）： No.3111. 10.3390/app11073111
16	YANG B， BENDER G， LE Q V， et al. CondConv： conditionally parameterized convolutions for efficient inference［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2019： 1307-1318. 10.48550/arXiv.1904.04971
17	CHEN Y P， DAI X Y， LIU M C， et al. Dynamic Convolution： attention over convolution kernels［C］// Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 11027-11036. 10.1109/cvpr42600.2020.01104
18	ZHANG Z H， JIA J L， WAN Y L， et al. TransR*： representation learning model by flexible translation and relation matrix projection［J］. Journal of Intelligent and Fuzzy Systems， 2021， 40（5）： 10251-10259. 10.3233/jifs-202177
19	RADEV D R， MUTHUKRISHNAN P， QAZVINIAN V， et al. The ACL anthology network corpus［J］. Language Resources and Evaluation， 2013， 47（4）： 919-944. 10.1007/s10579-012-9211-2
20	GUPTA S， VARMA V. Scientific article recommendation by using distributed representations of text and graph［C］// Proceedings of the 26th International Conference on World Wide Web Companion. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2017： 1267-1268. 10.1145/3041021.3053062
21	XUE G T， ZHONG M， LI J X， et al. Dynamic network embedding survey［J］. Neurocomputing， 2022， 472： 212-223. 10.1016/j.neucom.2021.03.138
22	LAURIOLA I， LAVELLI A， AIOLLI F. An introduction to deep learning in natural language processing： models， techniques， and tools［J］. Neurocomputing， 2022， 470： 443-456. 10.1016/j.neucom.2021.05.103
23	DONG Y X， CHAWLA N V， SWAMI A. Metapath2vec： scalable representation learning for heterogeneous networks［C］// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2017： 135-144. 10.1145/3097983.3098036
24	BHAGAVATULA C， FELDMAN S， POWER R， et al. Content-based citation recommendation［C］// Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1 （Long Papers）. Stroudsburg， PA： ACL， 2018： 238-251. 10.18653/v1/n18-1022
25	GUO Z W， WANG H. A deep graph neural network-based mechanism for social recommendations［J］. IEEE Transactions on Industrial Informatics， 2021， 17（4）： 2776-2783. 10.1109/tii.2020.2986316

数据集	论文数	作者数	引用数	关键词数
AAN	24 628	18 862	103 895	1 885
DBLP	51 040	25 981	364 778	3 903

数据集	论文数	作者数	引用数	关键词数
AAN	24 628	18 862	103 895	1 885
DBLP	51 040	25 981	364 778	3 903

模型	DBLP数据集							AAN数据集
模型	P@10	P@20	R@20	R@40	R@60	F1@20	MRR	P@10	P@20	R@20	R@40	R@60	F1@20	MRR
CATA++^［3］	0.186	0.151	0.124	0.179	0.238	0.147	0.435	0.191	0.128	0.164	0.218	0.252	0.144	0.461
DeepWalk^［21］	0.178	0.119	0.234	0.325	0.374	0.158	0.493	0.195	0.104	0.139	0.195	0.239	0.119	0.473
Doc2vec^［22］	0.067	0.038	0.092	0.143	0.184	0.054	0.401	0.075	0.062	0.103	0.186	0.236	0.077	0.354
Metapath2vec^［23］	0.121	0.082	0.119	0.196	0.246	0.097	0.258	0.125	0.082	0.107	0.171	0.210	0.093	0.329
NNSelect^［24］	0.246	0.150	0.279	0.349	0.406	0.195	0.512	0.219	0.146	0.176	0.237	0.296	0.160	0.525
GNN-SoR^［25］	0.197	0.157	0.131	0.189	0.253	0.153	0.443	0.206	0.139	0.169	0.225	0.260	0.153	0.453
C-KGAT	0.278	0.196	0.319	0.410	0.460	0.242	0.572	0.297	0.205	0.244	0.280	0.339	0.223	0.559

模型	DBLP数据集							AAN数据集
模型	P@10	P@20	R@20	R@40	R@60	F1@20	MRR	P@10	P@20	R@20	R@40	R@60	F1@20	MRR
CATA++^［3］	0.186	0.151	0.124	0.179	0.238	0.147	0.435	0.191	0.128	0.164	0.218	0.252	0.144	0.461
DeepWalk^［21］	0.178	0.119	0.234	0.325	0.374	0.158	0.493	0.195	0.104	0.139	0.195	0.239	0.119	0.473
Doc2vec^［22］	0.067	0.038	0.092	0.143	0.184	0.054	0.401	0.075	0.062	0.103	0.186	0.236	0.077	0.354
Metapath2vec^［23］	0.121	0.082	0.119	0.196	0.246	0.097	0.258	0.125	0.082	0.107	0.171	0.210	0.093	0.329
NNSelect^［24］	0.246	0.150	0.279	0.349	0.406	0.195	0.512	0.219	0.146	0.176	0.237	0.296	0.160	0.525
GNN-SoR^［25］	0.197	0.157	0.131	0.189	0.253	0.153	0.443	0.206	0.139	0.169	0.225	0.260	0.153	0.453
C-KGAT	0.278	0.196	0.319	0.410	0.460	0.242	0.572	0.297	0.205	0.244	0.280	0.339	0.223	0.559

模型	DBLP	AAN
C-KGAT/D	0.567	0.552
C-KGAT/P	0.559	0.547
C-KGAT	0.572	0.559

Citation recommendation algorithm fusing knowledge graph and graph attention network

融合知识图谱和图注意力网络的引文推荐算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 25

Related Articles 15

Recommended Articles

Metrics

[1]	Guixiang XUE, Hui WANG, Weifeng ZHOU, Yu LIU, Yan LI. Port traffic flow prediction based on knowledge graph and spatio-temporal diffusion graph convolutional network [J]. Journal of Computer Applications, 2024, 44(9): 2952-2957.
[2]	Zhizheng ZHANG, Xiaojian ZHANG, Junqing WANG, Guanghui FENG. Federated spatial data publication method with differential privacy and secure aggregation [J]. Journal of Computer Applications, 2024, 44(9): 2777-2784.
[3]	Jie WU, Ansi ZHANG, Maodong WU, Yizong ZHANG, Congbao WANG. Overview of research and application of knowledge graph in equipment fault diagnosis [J]. Journal of Computer Applications, 2024, 44(9): 2651-2659.
[4]	Hang YANG, Wanggen LI, Gensheng ZHANG, Zhige WANG, Xin KAI. Multi-layer information interactive fusion algorithm based on graph neural network for session-based recommendation [J]. Journal of Computer Applications, 2024, 44(9): 2719-2725.
[5]	Yubo ZHAO, Liping ZHANG, Sheng YAN, Min HOU, Mao GAO. Relation extraction between discipline knowledge entities based on improved piecewise convolutional neural network and knowledge distillation [J]. Journal of Computer Applications, 2024, 44(8): 2421-2429.
[6]	Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617.
[7]	Yangyi GAO, Tao LEI, Xiaogang DU, Suiyong LI, Yingbo WANG, Chongdan MIN. Crowd counting and locating method based on pixel distance map and four-dimensional dynamic convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2233-2242.
[8]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.
[9]	Sailong SHI, Zhiwen FANG. Gaze estimation model based on multi-scale aggregation and shared attention [J]. Journal of Computer Applications, 2024, 44(7): 2047-2054.
[10]	Zhangjian JI, Na DU. Tiny target detection based on improved VariFocalNet [J]. Journal of Computer Applications, 2024, 44(7): 2200-2207.
[11]	Youren YU, Yangsen ZHANG, Yuru JIANG, Gaijuan HUANG. Chinese named entity recognition model incorporating multi-granularity linguistic knowledge and hierarchical information [J]. Journal of Computer Applications, 2024, 44(6): 1706-1712.
[12]	Fanjun MENG, Bin HAN, Shucheng HUANG, Xiangdong MEI. Distributed temporal index for temporal aggregation range query [J]. Journal of Computer Applications, 2024, 44(6): 1848-1854.
[13]	Tianci KE, Jianhua LIU, Shuihua SUN, Zhixiong ZHENG, Zijie CAI. Aspect-level sentiment analysis model combining strong association dependency and concise syntax [J]. Journal of Computer Applications, 2024, 44(6): 1786-1795.
[14]	Jianjing LI, Guanfeng LI, Feizhou QIN, Weijun LI. Multi-relation approximate reasoning model based on uncertain knowledge graph embedding [J]. Journal of Computer Applications, 2024, 44(6): 1751-1759.
[15]	Wenping ZHENG, Huilin GE, Meilin LIU, Gui YANG. Node classification algorithm fusing 2-connected motif-structure information [J]. Journal of Computer Applications, 2024, 44(5): 1464-1470.