基于类传播分布的关系近邻异质性网络分类方法

doi:10.13229/j.cnki.jdxbgxb201602029

吉林大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (2): 522-527.doi: 10.13229/j.cnki.jdxbgxb201602029

基于类传播分布的关系近邻异质性网络分类方法

董飒¹, 刘大有¹, 李丽娜¹, 欧阳若川², 柴晓丽³

1.吉林大学计算机科学与技术学院,长春 130012;
2.中国第一汽车集团股份有限公司研发中心,长春 130011;
3.空军航空大学基础部计算机教研室,长春 130022

收稿日期:2014-11-24 出版日期:2016-02-20 发布日期:2016-02-20
通讯作者: 刘大有(1942-),男,教授,博士生导师.研究方向:人工智能,数据挖掘.E-mail:liudy@jlu.edu.cn E-mail:dongsa7701@163.com
作者简介:董飒(1985-),女,博士研究生.研究方向:数据挖掘.E-mail:dongsa7701@163.com
基金资助:
国家自然科学基金项目(61133011); 国家自然科学基金面上项目(61373053,61472161,61170092)

Relational neighbor algorithm based on class propagation distributions for classification in networked data with heterophily

DONG Sa¹, LIU Da-you¹, LI Li-na¹, OUYANG Ruo-chuan², CHAI Xiao-li³

1.College of Computer Science and Technology, Jilin University, Changchun 130012, China;
2.FAW Co., Ltd., Research and Development Center, Changchun 130011, China;
3.Computer Office, Aviation University of Air Force, Changchun 130022, China

Received:2014-11-24 Online:2016-02-20 Published:2016-02-20

摘要/Abstract

摘要： 基于同质性假设的关系分类方法对异质性网络分类性能较差,针对异质性网络的分类问题提出了一种基于类传播分布的关系近邻分类方法.该方法采用二阶马尔可夫假设,分类时考虑来自未标记结点邻居的邻居的影响,并通过计算传播类别向量和传播参考向量使结点间的影响进行传递,结合松弛标注的协作推理方法不断更新分类结果直至类分布收敛.对比实验结果表明,本文方法在异质性网络分类上具有较高的分类精度.

关键词: 人工智能, 异质性网络分类, 类传播分布关系近邻分类器, 协作推理

Abstract: The performance of the relational classifiers based on homophily is poor for the classification in networked data with heterophily. To solve this problem, a relational neighbor algorithm based on propagation distributions is proposed for heterophilous networks. The algorithm adopts the second-order Markov assumption and considers the influence from the neighbors of the unlabeled nodes' neighbors. At the same time the algorithm propagates the influence between nodes through computing propagating class vector and propagating reference vector; and by means of combining the relaxation labeling collective inference method, the algorithm continuously updates the results until the class distributions converge. Experiment results show that the proposed algorithm performs better on the networks with heterophily.

Key words: artificial Intelligence, heterophilous network classification, class propagating distribution relational neighbor classifier, collective inference

中图分类号:

TP301

董飒, 刘大有, 李丽娜, 欧阳若川, 柴晓丽. 基于类传播分布的关系近邻异质性网络分类方法[J]. 吉林大学学报(工学版), 2016, 46(2): 522-527.

DONG Sa, LIU Da-you, LI Li-na, OUYANG Ruo-chuan, CHAI Xiao-li. Relational neighbor algorithm based on class propagation distributions for classification in networked data with heterophily[J]. 吉林大学学报(工学版), 2016, 46(2): 522-527.

参考文献

[1] Chakrabarti S, Dom B, Indyk P. Enhanced hypertext categorization using hyperlinks[C]//In Proceedings of the 1998 ACM SIGMOD International Conference on Management of Data, New York, USA, 1998:307-319.
[2] Macskassy S A, Provost F. A simple relational classifier[C]//Proceedings of the Multi-Relational Data Mining Workshop at the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2003:64-76.
[3] Lu Q, Getoor L. Link-based classification[C]//Proceedings of 12th International Conference on Machine Learning (ICML),Washington DC, 2003:496-503.
[4] Perlich C, Provost F. Distribution-based aggregation for relational leaning with identifier attributes[J]. Machine Learning, 2006, 62(1/2):65-105.
[5] Perlich C, Provost F. Aggregation-based feature invention and relational concept classes[C]//Proceedings of 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington DC,2003:167-176.
[6] Macskassy S A, Provost F. Classification in networked data: A toolkit and a univariate case study[J]. Journal of Machine Learning Research, 2007, 8:935-983.
[7] McPherson M, Smith-Lovin L, Cook J M. Birds of a feather: homophily in social networks[J].Annual Review of Sociology, 2001, 27:415-444.
[8] Wang Zhen-wen, Yin Feng-jing, Tan Wen-tang, et al. Classification in networked data with heterophily[J]. The Scientific World Journal, 2013:236769.
[9] Lin F, Cohen W W. Semi-supervised classification of network data using very few labels[C]//In Proceedings of the International Conference on Advances in Social Network Analysis and Mining, IEEE Computer Society, Washington DC, USA, 2010, 10:192-199.
[10] 李丽娜. 基于链接的网络分类和链接预测新方法研究[D].长春:吉林大学计算机科学与技术学院,2012.
Li Li-na. Research on classification and link prediction of network data based on links[D]. Changchun: College of Computer Science and Technology, Jilin University, 2012.
[11] Geman S, Geman D. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 1984, 6: 721-741.
[12] Sen P, Namata G M, Bilgic M, et al. Eliassi-Rad. collective classication in network data[J]. AI Magazine, 2008, 29(3):93-106.

相关文章 15

[1]	董飒, 刘大有, 欧阳若川, 朱允刚, 李丽娜. 引入二阶马尔可夫假设的逻辑回归异质性网络分类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1571-1577.
[2]	顾海军, 田雅倩, 崔莹. 基于行为语言的智能交互代理[J]. 吉林大学学报(工学版), 2018, 48(5): 1578-1585.
[3]	王旭, 欧阳继红, 陈桂芬. 基于垂直维序列动态时间规整方法的图相似度度量[J]. 吉林大学学报(工学版), 2018, 48(4): 1199-1205.
[4]	张浩, 占萌苹, 郭刘香, 李誌, 刘元宁, 张春鹤, 常浩武, 王志强. 基于高通量数据的人体外源性植物miRNA跨界调控建模[J]. 吉林大学学报(工学版), 2018, 48(4): 1206-1213.
[5]	黄岚, 纪林影, 姚刚, 翟睿峰, 白天. 面向误诊提示的疾病-症状语义网构建[J]. 吉林大学学报(工学版), 2018, 48(3): 859-865.
[6]	李雄飞, 冯婷婷, 骆实, 张小利. 基于递归神经网络的自动作曲算法[J]. 吉林大学学报(工学版), 2018, 48(3): 866-873.
[7]	刘杰, 张平, 高万夫. 基于条件相关的特征选择方法[J]. 吉林大学学报(工学版), 2018, 48(3): 874-881.
[8]	王旭, 欧阳继红, 陈桂芬. 基于多重序列所有公共子序列的启发式算法度量多图的相似度[J]. 吉林大学学报(工学版), 2018, 48(2): 526-532.
[9]	杨欣, 夏斯军, 刘冬雪, 费树岷, 胡银记. 跟踪-学习-检测框架下改进加速梯度的目标跟踪[J]. 吉林大学学报(工学版), 2018, 48(2): 533-538.
[10]	刘雪娟, 袁家斌, 许娟, 段博佳. 量子k-means算法[J]. 吉林大学学报(工学版), 2018, 48(2): 539-544.
[11]	曲慧雁, 赵伟, 秦爱红. 基于优化算子的快速碰撞检测算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1598-1603.
[12]	李嘉菲, 孙小玉. 基于谱分解的不确定数据聚类方法[J]. 吉林大学学报(工学版), 2017, 47(5): 1604-1611.
[13]	邵克勇, 陈丰, 王婷婷, 王季驰, 周立朋. 无平衡点分数阶混沌系统全状态自适应控制[J]. 吉林大学学报(工学版), 2017, 47(4): 1225-1230.
[14]	王生生, 王创峰, 谷方明. OPRA方向关系网络的时空推理[J]. 吉林大学学报(工学版), 2017, 47(4): 1238-1243.
[15]	马淼, 李贻斌. 基于多级图像序列和卷积神经网络的人体行为识别[J]. 吉林大学学报(工学版), 2017, 47(4): 1244-1252.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于类传播分布的关系近邻异质性网络分类方法

Relational neighbor algorithm based on class propagation distributions for classification in networked data with heterophily

RICH HTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10