基于特征对比学习和图卷积的社交网络用户分类

doi:10.19678/j.issn.1000-3428.0067327

摘要/Abstract

摘要： 社交网络用户分类旨在通过用户属性和社交关系确定用户的兴趣爱好,可通过图类数据的节点分类实现。多数基于图卷积神经网络(GCN)的节点分类方法仅能处理高同质率数据集,但社交网络数据集通常具有较高的异质率。针对社交网络数据集同质率较低的问题,提出一种基于特征对比学习的图卷积神经网络(CLGCN)模型。通过预训练的组合标签构造相似性矩阵,根据相似性矩阵进行图卷积。利用特征对比学习分别定义类别相同和不同的邻居节点对为正负样本对,最小化特征对比的损失函数,使同类节点对的特征表达相似性更高及异类节点对的特征表达可区分性更强。实验结果表明,CLGCN模型在3个低同质率社交网络数据集上的节点分类准确率分别达到93.5%、81.4%和67.9%,均高于对比模型。

关键词: 社交网络, 对比学习, 同质率, 图卷积神经网络, 节点分类

Abstract: The user classification of social networks aims to determine the interests and hobbies of users through their personal attributes and social relations. This can be regarded as a node classification problem for graph data. Most node classification algorithms based on Graph Convolutional Neural Network(GCN) can handle datasets with high heterogeneity. However, social network datasets often exhibit high heterogeneity rate. This study proposes a feature Contrastive Learning-based GCN(CLGCN) model to alleviate this problem. A similarity matrix is constructed from the combined labels during the pretraining stage and used to perform graph convolution operation. Node pairs of features are defined as positive or negative sample pairs based on whether they belong to the same or different categories, respectively, using feature contrastive learning. Consequently, the representations of node pairs from the same category become more similar, whereas those of node pairs from different categories become more distinguishable by minimizing the loss function of feature contrastive learning. The experimental results on three low homogeneity rate social network datasets demonstrate that the accuracies of the proposed model for node classification are 93.5%, 81.4%, and 67.9%, respectively, which are all better than those of the other comparative models.

Key words: social network, contrastive learning, homogeneity rate, Graph Convolutional Neural Network(GCN), node classification

中图分类号:

TP399

李政学, 李枝名, 彭德中, 陈杰. 基于特征对比学习和图卷积的社交网络用户分类[J]. 计算机工程, 2024, 50(4): 258-266.

LI Zhengxue, LI Zhiming, PENG Dezhong, CHEN Jie. User Classification of Social Networks Based on Feature Contrastive Learning and Graph Convolution[J]. Computer Engineering, 2024, 50(4): 258-266.

https://www.ecice06.com/CN/Y2024/V50/I4/258

参考文献

[1] 邵云飞, 宋友, 王宝会. 基于社交网络图节点度的神经网络个性化传播算法研究[J]. 计算机科学, 2023, 50(4):16-21. SHAO Y F, SONG Y, WANG B H. Study on degree of node based personalized propagation of neural predictions for social networks[J]. Computer Science, 2023, 50(4):16-21.(in Chinese)
[2] CAN U, ALATAS B. A new direction in social network analysis:online social network analysis problems and applications[J]. Physica A:Statistical Mechanics and Its Applications, 2019, 535:122372.
[3] OLANREWAJU A S T, HOSSAIN M A, WHITESIDE N, et al. Social media and entrepreneurship research:a literature review[J]. International Journal of Information Management, 2020, 50:90-110.
[4] 龙增艳, 陈志刚, 徐成林. 基于用户交互的社交网络好友推荐算法[J]. 计算机工程, 2019, 45(3):132-137. LONG Z Y, CHEN Z G, XU C L. Social network friend recommendation algorithm based on user interaction[J]. Computer Engineering, 2019, 45(3):132-137.(in Chinese)
[5] 黄鑫, 李赟, 熊瑾煜. 基于信息传播节点集的CTDN节点分类算法[J]. 计算机工程, 2021, 47(6):188-196. HUANG X, LI Y, XIONG J Y. Node classification algorithm based on information propagation node set for CTDN[J]. Computer Engineering, 2021, 47(6):188-196.(in Chinese)
[6] ZHU J, YAN Y J, ZHAO L X, et al. Beyond homophily in graph neural networks:current limitations and effective designs[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York, USA:ACM Press, 2020:7793-7804.
[7] 张陶, 于炯, 廖彬, 等. 基于图嵌入与支持向量机的社交网络节点分类方法[J]. 计算机应用研究, 2021, 38(9):2646-2650, 2661. ZHANG T, YU J, LIAO B, et al. Node classification method in social network based on graph embedding and support vector machine[J]. Application Research of Computers, 2021, 38(9):2646-2650, 2661.(in Chinese)
[8] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA:ACM Press, 2014:701-710.
[9] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL].[2023-03-11]. https://arxiv.org/abs/1301.3781.
[10] GROVER A, LESKOVEC J. Node2Vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA:ACM Press, 2016:855-864.
[11] GILMER J, SCHOENHOLZ S S, RILEY P F, et al. Neural message passing for quantum chemistry[C]//Proceedings of the 34th International Conference on Machine Learning. New York, USA:ACM Press, 2017:1263-1272.
[12] NG A. Sparse autoencoder[EB/OL].[2023-03-11]. https://web.stanford.edu/class/cs294a/sparseAutoencoder.pdf.
[13] 李盼, 解庆, 李琳, 等. 知识增强的图神经网络序列推荐模型[J]. 计算机工程, 2023, 49(2):70-80. LI P, XIE Q, LI L, et al. Knowledge-enhanced graph neural network model for sequential recommendation[J]. Computer Engineering, 2023, 49(2):70-80.(in Chinese)
[14] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL].[2023-03-11]. https://arxiv.org/pdf/1609.02907.pdf.
[15] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL].[2023-03-11]. https://arxiv.org/pdf/1710.10903.pdf.
[16] HE D X, LIANG C D, LIU H X, et al. Block modeling-guided graph convolutional neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence. Palo Alto, USA:AAAI Press, 2022:4022-4029.
[17] CHUANG C Y, ROBINSON J, LIN Y C, et al. Debiased contrastive learning[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York, USA:ACM Press, 2020:8765-8775
[18] YOU Y, CHEN T, SUI Y, et al. Graph contrastive learning with augmentations[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York, USA:ACM Press, 2020:5812-5823.
[19] XU J, TANG H Y, REN Y Z, et al. Multi-level feature learning for contrastive multi-view clustering[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA:IEEE Press, 2022:16051-16060.
[20] DE BOER P T, KROESE D P, MANNOR S, et al. A tutorial on the cross-entropy method[J]. Annals of Operations Research, 2005, 134(1):19-67.
[21] VELICKOVIC P, FEDUS W, HAMILTON W L, et al. Deep graph infomax[EB/OL].[2023-03-11]. https://arxiv.org/pdf/1809.10341.pdf.
[22] SUN F Y, HOFFMAN J, VERMA V, et al. InfoGraph:unsupervised and semi-supervised graph-level representation learning via mutual information maximization[EB/OL].[2023-03-11]. https://arxiv.org/pdf/1908.01000.pdf.
[23] THAKOOR S, TALLEC C, AZAR M G, et al. Bootstrapped representation learning on graphs[EB/OL].[2023-03-11]. https://arxiv.org/pdf/2207.05969.pdf.
[24] VERLEYSEN M, FRANÇOIS D. The curse of dimensionality in data mining and time series prediction[C]//Proceedings of the 8th Biennial Meeting of the International Work-Conference on Artificial Neural Networks. Berlin, Germany:Springer, 2005:758-770.
[25] GUO K, ZHOU K, HU X, et al. Orthogonal graph neural networks[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto, USA:AAAI Press, 2022:3996-4004.
[26] ABU-EL-HAIJA S, PEROZZI B, KAPOOR A, et al. MixHop:higher-order graph convolutional architectures via sparsified neighborhood mixing[EB/OL].[2023-03-11]. https://arxiv.org/pdf/1905.00067.pdf.
[27] ZHAO T, LIU Y, NEVES L, et al. Data augmentation for graph neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence. Palo Alto, USA:AAAI Press, 2021:11015-11023.
[28] WANG X, ZHU M Q, BO D Y, et al. AM-GCN:adaptive multi-channel graph convolutional networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, USA:ACM Press, 2020:1243-1253.

选择文件类型/文献管理软件名称

选择包含的内容