一种用于图卷积网络的社交关系方向门控算法

doi:10.13190/j.jbupt.2020-074

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (5): 77-83.doi: 10.13190/j.jbupt.2020-074

一种用于图卷积网络的社交关系方向门控算法

李蕾, 谢旸, 蒋亚飞, 刘咏彬

北京邮电大学人工智能学院, 北京 100876

收稿日期:2020-06-25 发布日期:2021-03-11
作者简介:李蕾(1974-),女,副教授,硕士生导师,E-mail:leili@bupt.edu.cn.
基金资助:
国家自然科学基金项目（91546121，71231002）；北京市科学技术委员会项目（Z181100001018035）

A Social Relationship Direction Gating Algorithm for Graph Convolutional Networks

LI Lei, XIE Yang, JIANG Ya-fei, LIU Yong-bin

School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2020-06-25 Published:2021-03-11

摘要/Abstract

摘要： 针对社交网络用户态度分析任务中用户之间原有社交关系方向可能阻碍态度信息流动以及标签扩散的问题，提出了一种应用于半监督图卷积网络的社交关系方向门控算法.该算法首先在原有与逆向社交关系方向上分别进行图卷积运算，得到2种用户节点态度特征向量，然后利用门控机制对2种特征向量进行动态融合.扩展了态度信息传播路径的同时，还能够捕捉用户影响力差异，以自动选择态度信息的流动方向.在2个真实热点话题数据集上的实验结果表明，现有图卷积网络在加入该算法之后，其用户态度分析的准确率能够得到有效提升.

关键词: 图卷积网络, 门控算法, 用户态度分析, 社交网络

Abstract: Facing the problem in social user attitude analysis that the original social relationship direction between users in social networks hinders the flow of attitude information and label propagation, a social relationship direction gating algorithm for graph convolutional networks is proposed. The algorithm first performs graph convolution on the origin and reverse social relationship directions to obtain two types of user node attitude feature vectors, and then leverages the gating mechanism to integrate the feature vectors dynamically. While expanding the propagation of attitude information, the algorithm can also capture the differences of user influence to automatically select the flow of attitude information. Experiments on two real hot topic datasets show that the accuracy of the existing graph convolutional networks can be effectively improved after adding the proposed algorithm.

Key words: graph convolutional network, gating algorithm, user attitude analysis, social network

中图分类号:

TP391

李蕾, 谢旸, 蒋亚飞, 刘咏彬. 一种用于图卷积网络的社交关系方向门控算法[J]. 北京邮电大学学报, 2020, 43(5): 77-83.

LI Lei, XIE Yang, JIANG Ya-fei, LIU Yong-bin. A Social Relationship Direction Gating Algorithm for Graph Convolutional Networks[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 77-83.

参考文献

[1] Bing Liu. Sentiment analysis and opinion mining[J]. Synthesis Lectures on Human Language Technologies, 2012, 5(1):1-167.[LinkOut]
[2] Myers D G. Social psychology[M]. New York:Mcgraw-Hill, 2009:124.
[3] 李勇敢, 周学广, 孙艳, 等. 中文微博情感分析研究与实现[J]. 软件学报, 2017, 28(12):3183-3205. Li Yonggan, Zhou Xueguang, Sun Yan, et al. Research and implementation of Chinese microblog sentiment classification[J]. Journal of Software, 2017, 28(12):3183-3205.
[4] 李婷婷, 姬东鸿. 基于SVM和CRF多特征组合的微博情感分析[J]. 计算机应用研究, 2015, 32(4):978-981. Li Tingting, Ji Donghong. Sentiment analysis of micro-blog based on SVM and CRF using various combinations of features[J]. Application Research of Computers, 2015, 32(4):978-981.
[5] 周瑛, 刘越, 蔡俊. 基于注意力机制的微博情感分析[J]. 情报理论与实践, 2018, 41(3):89-94. Zhou Ying, Liu Yue, Cai Jun. Sentiment analysis of micro-blogs based on attention mechanism[J]. Information Studies (Theory & Application), 2018, 41(3):89-94.
[6] 杜慧, 俞晓明, 刘悦, 等. 融合词性和注意力的卷积神经网络对象级情感分类方法[J]. 模式识别与人工智能, 2018, 31(12):1120-1126. Du Hui, Yu Xiaoming, Liu Yue, et al. CNN with part-of-speech and attention mechanism for targeted sentiment classification[J]. Pattern Recognition and Artificial Intelligence, 2018, 31(12):1120-1126.
[7] 孙晓, 彭晓琪, 胡敏, 等. 基于多维扩展特征与深度学习的微博短文本情感分析[J]. 电子与信息学报, 2017, 39(9):2048-2055. Sun Xiao, Peng Xiaoqi, Hu Min, et al. Extended multi-modality features and deep learning based microblog short text sentiment analysis[J]. Journal of Electronics & Information Technology, 2017, 39(9):2048-2055.
[8] West R, Paskov H S, Leskovec J, et al. Exploiting social network structure for person-to-person sentiment analysis[J]. Transactions of the Association for Computational Linguistics, 2014, 2:297-310.
[9] 黄丹阳, 王菲菲, 杨扬, 等. 基于网络结构与用户内容的动态兴趣识别方法[J]. 北京邮电大学学报, 2018, 41(2):103-108. Huang Danyang, Wang Feifei, Yang Yang, et al. Dynamic interest identification based on social network structure and user generated contents[J]. Journal of Beijing University of Posts and Telecommunications, 2018, 41(2):103-108.
[10] Zhu X, Ghahramani Z, Lafferty J D. Semi-supervised learning using gaussian fields and harmonic functions[C]//Proceedings of the 20th International Conference on Machine Learning (ICML-03). Washington, DC:AAAI Press, 2003:912-919.
[11] Chapelle O, Zien A. Semi-supervised classification by low density separation[C]//AISTATS.2005:57-64.
[12] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[EB/OL]. 2016(2016-09-06)[2020-06-25]. https://arxiv.org/abs/1609.02907.
[13] Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graphs[EB/OL]. 2017(2017-06-07)[2020-06-25]. https://arxiv.org/abs/1706.02216.
[14] Veličković P, Cucurull G, Casanova A, et al. Graph attention networks[EB/OL]. 2017(2017-10-30)[2020-06-25]. https://arxiv.org/abs/1710.10903.
[15] Li Q, Han Z, Wu X M. Deeper insights into graph convolutional networks for semi-supervised learning[C]//Thirty-Second AAAI Conference on Artificial Intelligence. Palo Alto:Association for the Advancement of Artificial Intelligence, 2018:3538-3545.
[16] Yang Zhilin, Cohen W W, Salakhutdinov R. Revisiting semi-supervised learning with graph embeddings[EB/OL]. 2016(2016-03-29)[2020-06-25]. https://arxiv.org/abs/1603.08861.
[17] Kingma D P, Ba J. Adam:a method for stochastic optimization[EB/OL]. 2014(2014-12-22)[2020-06-25]. https://arxiv.org/abs/1412.6980.
[18] Kim Y. Convolutional neural networks for sentence classification[EB/OL]. 2014(2014-08-25)[2020-06-25]. https://arxiv.org/abs/1408.5882.
[19] Huang Z, Xu W, Yu K. Bidirectional LSTM-CRF models for sequence tagging[EB/OL]. 2015(2015-08-09)[2020-06-25]. https://arxiv.org/abs/1508.01991.
[20] Joulin A, Grave E, Bojanowski P, et al. Bag of tricks for efficient text classification[EB/OL]. 2016(2016-07-06)[2020-06-25]. https://arxiv.org/abs/1607.01759.
[21] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. Red Hook:Curran Associates Inc, 2017:6000-6010.

一种用于图卷积网络的社交关系方向门控算法

A Social Relationship Direction Gating Algorithm for Graph Convolutional Networks

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 11

编辑推荐

Metrics

本文评价

[1]	黄跃珍戴晶帼张承业魏东. 基于关联图关键边发现的人脸图像聚类算法[J]. 北京邮电大学学报, 2023, 46(1): 97-102.
[2]	王文竹, 肖波, 陈柯宏. 一种面向目标的情感极性分析方法[J]. 北京邮电大学学报, 2021, 44(5): 21-27.
[3]	王艺霏, 莫爽, 吴文睿, 范少华, 肖丁. 基于内外卷积网络的网络入侵检测[J]. 北京邮电大学学报, 2021, 44(5): 94-100.
[4]	张栋, 陈鸿龙. 融合文本信息的轻量级图卷积网络推荐模型[J]. 北京邮电大学学报, 2021, 44(5): 88-93.
[5]	徐九韵, 孙忠顺, 张如如. 基于链路预测的手机节能方法[J]. 北京邮电大学学报, 2020, 43(1): 8-13,27.
[6]	冀振燕, 宋晓军, 皮怀雨, 杨春. 基于深度学习的融合多源异构数据的推荐模型[J]. 北京邮电大学学报, 2019, 42(6): 35-42.
[7]	徐前方, 王嘉春, 肖波. 融合时空上下文信息的兴趣点推荐[J]. 北京邮电大学学报, 2018, 41(1): 37-42,50.
[8]	王青山, 汤颖, 王琦, 王翟, 陈莉君. 校园移动社交网络中基于种子的数据分发算法[J]. 北京邮电大学学报, 2017, 40(2): 97-101.
[9]	杨学成, 陶晓波, 岳欣. 双有限异质社交网络仿真建模及实证分析[J]. 北京邮电大学学报, 2015, 38(s1): 121-124.
[10]	徐雅斌, 孙晓晨. 位置社交网络的个性化位置推荐[J]. 北京邮电大学学报, 2015, 38(5): 118-124.
[11]	张维玉, 吴斌, 刘旸. 融合多特征的符号网络连边符号预测[J]. 北京邮电大学学报, 2014, 37(5): 80-84.