基于动态负采样的图卷积协同过滤推荐模型

doi:10.11896/jsjkx.230200149

摘要/Abstract

摘要： 负采样对协同过滤算法的准确性有很大的影响。针对现有的图卷积网络缺乏对负采样策略的探索这一问题,提出一种基于动态负采样的图卷积协同过滤推荐模型(Dynamic Negative Sampling-Based Graph Convolution Collaborative Filtering Recommendation Model,DGCCF)。首先,为了能更灵活地适应不同图数据的需求,在图卷积网络中引入归一化参数来调节节点进行信息传递时邻域对其的影响;其次,提出一种动态负采样策略,从用户未交互过的物品节点中选取负样本集,经过图卷积后得到负样本评分,选取评分最高的负样本作为难负样本;最后,将得到的难负样本和正样本作为样本对输入贝叶斯个性化排序函数,对模型进行优化。在Gowalla,Yelp2018和Amazon-Book 3个公开数据集上与基线模型进行的对比实验表明,DGCCF在多个评价指标下均优于现有的基线方法,在3个数据集上,召回率分别比最优基线提升了0.3%,9.4%和10.6%。

关键词: 协同过滤, 图卷积神经网络, 负采样, 推荐系统, 评分预测

Abstract: Negative sampling has a great impact on the accuracy of collaborative filtering algorithms,to solve the problem that the existing graph convolutional network lacks the exploration of negative sampling strategies,dynamic negative sampling-based graph convolution collaborative filtering recommendation model(DGCCF) is proposed.Firstly,in order to adapt more flexibly to the needs of different graph data,a normalization parameter is introduced in the graph convolutional network to adjust the influen-ce of the neighborhood.Secondly,a dynamic negative sampling strategy is proposed,which selects a set of negative samples from the item nodes that the user has not interacted with,and after graph convolution gets the negative sample score,selects the negative sample with the highest score as the hard negative sample,and finally uses the obtained hard negative sample and positive sample as samplesets to input the Bayesian personalized ranking function to optimize the model.Comparison experiments with the baseline model on the three public datasets Gowalla,Yelp2018 and Amazon-Book show that DGCCF is superior to existing baseline methods under multiple evaluation indicators.For example,compared to the optimal baseline,its recall rate increases by 0.3%,9.4%,and 10.6% respectively on three dataset.

Key words: Collaborative filtering, Graph convolutional neural network, Negative sampling, Recommendation system, Score prediction

中图分类号:

TP391

马汉达, 方雨清. 基于动态负采样的图卷积协同过滤推荐模型[J]. 计算机科学, 2023, 50(11A): 230200149-7. https://doi.org/10.11896/jsjkx.230200149

MA Handa, FANG Yuqing. Dynamic Negative Sampling for Graph Convolution Network Based Collaborative Filtering Recommendation Model[J]. Computer Science, 2023, 50(11A): 230200149-7. https://doi.org/10.11896/jsjkx.230200149

参考文献

[1]MA H D,JING D.A microblog friend recommendation algorithm-based on SSD and timing model[J].Computer Engineering & Science,2021,43(7):1291-1298.
[2]CHENG Z T,ZHONG T,ZHANG S M,et al.Survey of Recom-mender Systems Based on Graph Learning[J].Computer Scien-ce,2022,49(9):1-13.
[3]WU S,SUN F,ZHANG W,et al.Graph neural networks in re-commender systems:a survey[J].ACM Computing Surveys,2022,55(5):1-37.
[4]WANG X,HE X,WANG M,et al.Neural graph collaborativefiltering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
[5]HE X,DENG K,WANG X,et al.Lightgcn:Simplifying andpowering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:639-648.
[6]YING R,HE R,CHEN K,et al.Graph convolutional neural networks for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:974-983.
[7]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.Bayesian personalized ranking from implicit feedback[C]//Proc.of Uncertainty in Artificial Intelligence.2014:452-461.
[8]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[9]KIM D,PARK C,OH J,et al.Convolutional matrix factorization for document context-aware recommendation[C]//Proceedings of the 10th ACM Conference on Recommender Systems.2016:233-240.
[10]HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.2017:173-182.
[11]EBESU T,SHEN B,FANG Y.Collaborative memory network for recommendation systems[C]//The 41st international ACM SIGIR Conference on Research & Development in Information Retrieval.2018:515-524.
[12]SUN J,ZHANG Y,MA C,et al.Multi-graph convolution colla-borative filtering[C]//2019 IEEE International Conference on Data Mining(ICDM).IEEE,2019:1306-1311.
[13]TAN Q,LIU N,ZHAO X,et al.Learning to hash with graph neural networks for recommender systems[C]//Proceedings of The Web Conference 2020.2020:1988-1998.
[14]ZHANG Y,WANG P,ZHAO X,et al.IA-GCN:InteractiveGraph Convolutional Network for Recommendation[J].arXiv:2204.03827,2022.
[15]GONG K,SONG X,WANG S,et al.ITSM-GCN:InformativeTraining Sample Mining for Graph Convolutional Network-based Collaborative Filtering[C]//Proceedings of the 31st ACM International Conference on Information & Knowledge Management.2022:614-623.
[16]WANG X,JIN H,ZHANG A,et al.Disentangled graph collaborative filtering[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:1001-1010.
[17]WU J,HE X,WANG X,et al.Graph convolution machine for context-aware recommender system[J].Frontiers of Computer Science,2022,16(6):1-12.
[18]JIN B,GAO C,HE X,et al.Multi-behavior recommendationwith graph convolutional networks[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:659-668.
[19]CHEN L,WU L,HONG R,et al.Revisiting graph based colla-borative filtering:A linear residual graph convolutional network approach[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:27-34.
[20]DIAZ-AVILES E,DRUMOND L,SCHMIDT-THIEME L,et al.Real-time top-n recommendation in social streams[C]//Proceedings of the Sixth ACM Conference on Recommender Systems.2012:59-66.
[21]CUI P,LIU S,ZHU W.General knowledge embedded imagerepresentation learning[J].IEEE Transactions on Multimedia,2017,20(1):198-207.
[22]CAI T T,FRANKLE J,SCHWAB D J,et al.Are all negatives created equal in contrastive instance discrimination?[J].arXiv:2010.06682,2020.
[23]ZHANG W,CHEN T,WANG J,et al.Optimizing top-n collaborative filtering via dynamic negative item sampling[C]//Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval.2013:785-788.
[24]YANG Z,DING M,ZHOU C,et al.Understanding negativesampling in graph representation learning[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2020:1666-1676.
[25]WANG Y,LIU Z,FAN Z,et al.Dskreg:Differentiable sampling on knowledge graph for recommendation with relational gnn[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:3513-3517.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed