Collaborative Filtering Recommendation Algorithm Based on Graph Convolution Attention Neural Network

被引：2

作者：

Wang, Wei ^{[1
,2
,3
]}

Du, Yuxuan ^{[1
,2
]}

Zheng, Xiaoli ^{[1
,2
]}

Zhang, Chuang ^{[1
,2
]}

机构：

[1] School of Information & Electrical Engineering, Hebei University of Engineering, Hebei, Handan

[2] Hebei Key Laboratory of Security & Protection Information Sensing & Processing, Hebei University of Engineering, Hebei, Handan

[3] School of Internet of Things Engineering, Jiangnan University, Jiangsu, Wuxi

来源：

Computer Engineering and Applications | 2023年 / 59卷 / 13期

关键词：

attention mechanism; collaborative recommend; deep learning; graph convolution neural network; recommendation system;

D O I：

10.3778/j.issn.1002-8331.2206-0190

中图分类号：

学科分类号：

摘要：

With the rapid iterative development of information technology, the problem of information overload is becoming more and more serious. The recommendation algorithm can solve the information overload to a certain extent, but the traditional recommendation algorithm can not effectively solve the related problems such as data sparsity and recommendation accuracy. This paper proposes a graph convolution attention collaborative filtering(GCACF)recommendation method. Firstly, the model obtains the relevant interactive information of users and projects and transforms into corresponding feature vectors. Secondly, the feature vector aggregates with the propagation of graph convolution neural network and the attention mechanism redistributes the aggregated weight coefficients. Finally, the BPR loss function optimizes aggregated eigenvector and the model obtains the final recommendation result. Through the comparative experiments on Movielens-1M and Amazon-baby on two public datasets, GCACF is superior to the baseline method in precision, recall, Mrr, hit and NDCG. © 2023 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.

引用

页码：247 / 258

页数：11

共 45 条

[1]

STANLEY A J, CLIPSHAM P S., Information overload-myth or reality?, IEEE Colloquium on IT Strategies for Information Overload, (1998)

[2]

GARNER W., Search engines[J], Nursing Standard, 22, (2006)

[3]

WANG L, GAWTHROP P J., Data compression for estimation of the physical parameters of the SYSID’06 benchmark, IFAC Proceedings Volumes, 39, pp. 231-236, (2006)

[4]

BOCHKOV N P, SRAM R J, KULESHOV N P, Et al., System for the evaluation of the risk from chemical mutagens for man:Basic principles and practical recommendations[J], Mutation Research/Environmental Mutagenesis and Related Subjects, 38, 3, pp. 191-201, (1976)

[5]

LIU Y, WANG S L, ZHANG J F, Et al., A neural collaborative filtering method for identifying miRNA- disease associations[J], Neurocomputing, 422, pp. 176-185, (2021)

[6]

ANAND S T., Generating items recommendations by fusing content and user-item based collaborative filtering[J], Procedia Computer Science, 167, pp. 1934-1940, (2020)

[7]

CHEN H, QIAN F, CHEN J, Et al., Attribute-based neural collaborative filtering[J], Expert Systems with Applications, 185, 4, (2021)

[8]

SRINIVAS R, VERMA N, KRAKA E, Et al., Deep learning-based ligand design using shared latent implicit fingerprints from collaborative filtering[J], Journal of Chemical Information and Modeling, 61, 5, pp. 2159-2174, (2021)

[9]

LIU J., Score prediction based on matrix decomposition collaborative filtering algorithm, Journal of Scientific and Technological Innovation and Application, 5, (2016)

[10]

ANWAR T, UMA V, SRIVASTAVA G., Rec-CFSVD++: implementing recommendation system using collaborative filtering and singular value decomposition(SVD)++[J], International Journal of Information Technology and Decision Making, 2021, 4, pp. 1-19

← 1 2 3 4 5 →