搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于最大熵模型的导师-学生关系推测

李勇军 刘尊 于会

引用本文:
Citation:

基于最大熵模型的导师-学生关系推测

李勇军, 刘尊, 于会

Advisor-advisee relationship identification based on maximum entropy model

Li Yong-Jun, Liu Zun, Yu Hui
PDF
导出引用
  • 导师-学生关系是科研合作网络中重要的关系类型之一, 准确识别此类关系对促进科研交流与合作、评审回避等有重要意义. 以论文合作网络为基础, 依据学生发表论文时通常与导师共同署名的现象, 抽象出能够反映导师-学生合作关系的特征, 提出了基于最大熵模型的导师-学生关系识别算法. 利用DBLP中1990-2011年的论文数据进行实例验证, 结果显示: 1)关系类型识别结果的准确率超过95%; 2)导师-学生关系终止时间的平均误差为1.39年. 该方法在识别关系时避免了特征之间相互独立的约束, 准确率优于其他同类识别算法, 且建模方法对识别社交网络中的其他关系类型也具有借鉴意义.
    Research collaboration network has become an essential part in our academic activities. We can keep or develop collaboration relationships with other researchers or share research results with them within the research collaboration network. It is well generally accepted that different relationships have essentially different influences on the collaboration of researchers. Such a scenario also happens in our daily life. The advisor-advisee relationship plays an important role in the research collaboration network, so identification of advisor-advisee relationship can benefit the collaboration of researchers. In this paper, we aim to conduct a systematic investigation of the problem of indentifying the social relationship types from publication networks, and try to propose an easily computed and effective solution to this problem. Based on the common knowledge that graduate student always co-authors his papers with his advisor and not vice versa, our study starts with an analysis on publication network, and retrieves these features that can represent the advisor-advisee relationship. According to these features, an advisor-advisee relationship identification algorithm based on maximum entropy model with feature selection is proposed in this paper. We employ the DBLP dataset to test the proposed algorithm. The results show that 1) the mean of deviation of estimated end year to graduation year is 1.39; 2) the accuracy of advisor-advisee relationship identification results is more than 95%, and it is better than those of other algorithms obviously. Finally, the proposed algorithm can be extended to the relationship identification in online social network.
    • 基金项目: 西北工业大学基础研究基金(批准号: NPU-FFR-JC201257, JCY20130137)资助的课题.
    • Funds: Project supported by the Fundamental Research Foundation of Northwestern Polytechnical University, China (Grant Nos. NPU-FFR-JC201257, JCY20130137).
    [1]

    Bai M, Hu K, Tang Y 2011 Chin. Phys. B 20 12

    [2]

    Backstrom L, Leskovec J 2011 Proceedings of the 4th ACM International Conference on Web Search and Data Mining Hong Kong, China, February 9-12, 2011 pp635-644

    [3]

    Leskovec J, Huttenlocher D P, Kleinberg J M 2010 Proceedings of 19th International World Wide Web Conference Raleigh, USA, April 26-30, 2010 pp641-650

    [4]

    Diehl C P, Namata G, Getoor L 2007 Proceedings of Twenty-Second Conference on Artificial Intelligence Vancouver, Canada, July 22-26, 2007 pp546-552

    [5]

    Eagle N, Pentland A S, Lazer D 2009 Proc. Nat. Acad. Sci. U. S. A 106 36

    [6]

    Wang C, Han J, Jia Y, Tang J, Zhang D, Yu Y, Guo J 2010 Proceedings of 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Washington D.C., USA, July 24-28, 2010 pp203-212

    [7]

    Tang J, Lou T, Kleinberg J 2012 Proceedings of the 5th ACM International Conference on Web Search and Data Mining Seattle, USA, February 8-12, 2012 pp743-752

    [8]

    Tang S, Yuan J, Mao X, Li X, Chen W, Dai G 2011 Proceedings of 30th IEEE International Conference on Computer Communications Shanghai, China, April 10-15, 2011 pp1661-1669

    [9]

    Zhang Y Ch, Liu Y, Zhang H F, Cheng H, Xiong F 2012 Acta Phys. Sin. 60 050501(in Chinese) [张彦超, 刘云, 张海峰, 程辉, 熊菲 2012 物理学报 60 050501]

    [10]

    Gu Y R, Xia L L 2012 Acta Phys. Sin. 61 238701 (in Chinese) [顾亦然, 夏玲玲 2012 物理学报 61 238701]

    [11]

    Yu H, Liu Z, Li Y J 2013 Acta Phys. Sin. 62 020204 (in Chinese) [于会, 刘尊, 李勇军 2013 物理学报 62 020204]

    [12]

    Wu T Y, Chen Y G, Han J W 2010 Data Min. Knowl. Disc. 21 3

    [13]

    Byrd R H, Nocedal J, Schnabel R B 1994 Mathematical Programming A, B 63 4

  • [1]

    Bai M, Hu K, Tang Y 2011 Chin. Phys. B 20 12

    [2]

    Backstrom L, Leskovec J 2011 Proceedings of the 4th ACM International Conference on Web Search and Data Mining Hong Kong, China, February 9-12, 2011 pp635-644

    [3]

    Leskovec J, Huttenlocher D P, Kleinberg J M 2010 Proceedings of 19th International World Wide Web Conference Raleigh, USA, April 26-30, 2010 pp641-650

    [4]

    Diehl C P, Namata G, Getoor L 2007 Proceedings of Twenty-Second Conference on Artificial Intelligence Vancouver, Canada, July 22-26, 2007 pp546-552

    [5]

    Eagle N, Pentland A S, Lazer D 2009 Proc. Nat. Acad. Sci. U. S. A 106 36

    [6]

    Wang C, Han J, Jia Y, Tang J, Zhang D, Yu Y, Guo J 2010 Proceedings of 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Washington D.C., USA, July 24-28, 2010 pp203-212

    [7]

    Tang J, Lou T, Kleinberg J 2012 Proceedings of the 5th ACM International Conference on Web Search and Data Mining Seattle, USA, February 8-12, 2012 pp743-752

    [8]

    Tang S, Yuan J, Mao X, Li X, Chen W, Dai G 2011 Proceedings of 30th IEEE International Conference on Computer Communications Shanghai, China, April 10-15, 2011 pp1661-1669

    [9]

    Zhang Y Ch, Liu Y, Zhang H F, Cheng H, Xiong F 2012 Acta Phys. Sin. 60 050501(in Chinese) [张彦超, 刘云, 张海峰, 程辉, 熊菲 2012 物理学报 60 050501]

    [10]

    Gu Y R, Xia L L 2012 Acta Phys. Sin. 61 238701 (in Chinese) [顾亦然, 夏玲玲 2012 物理学报 61 238701]

    [11]

    Yu H, Liu Z, Li Y J 2013 Acta Phys. Sin. 62 020204 (in Chinese) [于会, 刘尊, 李勇军 2013 物理学报 62 020204]

    [12]

    Wu T Y, Chen Y G, Han J W 2010 Data Min. Knowl. Disc. 21 3

    [13]

    Byrd R H, Nocedal J, Schnabel R B 1994 Mathematical Programming A, B 63 4

  • [1] 李鑫, 赵城利, 刘阳洋. 有限步传播范围期望指标判别节点传播影响力. 物理学报, 2020, 69(2): 028901. doi: 10.7498/aps.69.20191313
    [2] 康志伟, 刘拓, 刘劲, 马辛, 陈晓. 基于自归一化神经网络的脉冲星候选体选择. 物理学报, 2020, 69(6): 069701. doi: 10.7498/aps.69.20191582
    [3] 梁潇, 钱志鸿, 田洪亮, 王雪. 基于马尔可夫决策模型的异构无线网络切换选择算法. 物理学报, 2016, 65(23): 236402. doi: 10.7498/aps.65.236402
    [4] 吴越, 杜亚军, 陈晓亮, 李显勇. 基于新曝光冲突性消息的网络舆论逆转研究. 物理学报, 2016, 65(3): 030502. doi: 10.7498/aps.65.030502
    [5] 李勇军, 尹超, 于会, 刘尊. 基于最大熵模型的微博传播网络中的链路预测. 物理学报, 2016, 65(2): 020501. doi: 10.7498/aps.65.020501
    [6] 王金龙, 刘方爱, 朱振方. 一种基于用户相对权重的在线社交网络信息传播模型. 物理学报, 2015, 64(5): 050501. doi: 10.7498/aps.64.050501
    [7] 王亚奇, 王静, 杨海滨. 基于复杂网络理论的微博用户关系网络演化模型研究. 物理学报, 2014, 63(20): 208902. doi: 10.7498/aps.63.208902
    [8] 蔡萌, 杜海峰, 费尔德曼. 一种基于最大流的网络结构熵. 物理学报, 2014, 63(6): 060504. doi: 10.7498/aps.63.060504
    [9] 王超, 刘骋远, 胡元萍, 刘志宏, 马建峰. 社交网络中信息传播的稳定性研究. 物理学报, 2014, 63(18): 180501. doi: 10.7498/aps.63.180501
    [10] 黄飞虎, 彭舰, 宁黎苗. 基于信息熵的社交网络观点演化模型. 物理学报, 2014, 63(16): 160501. doi: 10.7498/aps.63.160501
    [11] 王辉, 韩江洪, 邓林, 程克勤. 基于移动社交网络的谣言传播动力学研究. 物理学报, 2013, 62(11): 110505. doi: 10.7498/aps.62.110505
    [12] 肖延东, 老松杨, 侯绿林, 白亮. 一种基于网络最大可控子图的导航搜索模型. 物理学报, 2013, 62(24): 248901. doi: 10.7498/aps.62.248901
    [13] 王萍, 潘跃. 基于显著性特征的大冰雹识别模型. 物理学报, 2013, 62(6): 069202. doi: 10.7498/aps.62.069202
    [14] 刘群, 易佳. 基于演化博弈的社交网络模型演化研究. 物理学报, 2013, 62(23): 238902. doi: 10.7498/aps.62.238902
    [15] 赵佳, 喻莉, 李静茹. 社交网络中基于贝叶斯和半环代数模型的节点影响力计算机理. 物理学报, 2013, 62(13): 130201. doi: 10.7498/aps.62.130201
    [16] 顾亦然, 夏玲玲. 在线社交网络中谣言的传播与抑制. 物理学报, 2012, 61(23): 238701. doi: 10.7498/aps.61.238701
    [17] 梁义, 王兴元. 基于低阶矩阵最大特征值的复杂网络牵制混沌同步. 物理学报, 2012, 61(3): 038901. doi: 10.7498/aps.61.038901
    [18] 熊熙, 胡勇. 基于社交网络的观点传播动力学研究. 物理学报, 2012, 61(15): 150509. doi: 10.7498/aps.61.150509
    [19] 张彦超, 刘云, 张海峰, 程辉, 熊菲. 基于在线社交网络的信息传播模型. 物理学报, 2011, 60(5): 050501. doi: 10.7498/aps.60.050501
    [20] 申金媛, 李现国, 常胜江, 张延炘. 相位特征在三维物体识别中的应用. 物理学报, 2005, 54(11): 5157-5163. doi: 10.7498/aps.54.5157
计量
  • 文章访问数:  2992
  • PDF下载量:  479
  • 被引次数: 0
出版历程
  • 收稿日期:  2013-04-16
  • 修回日期:  2013-05-06
  • 刊出日期:  2013-08-05

基于最大熵模型的导师-学生关系推测

  • 1. 西北工业大学计算机学院, 西安 710072
    基金项目: 西北工业大学基础研究基金(批准号: NPU-FFR-JC201257, JCY20130137)资助的课题.

摘要: 导师-学生关系是科研合作网络中重要的关系类型之一, 准确识别此类关系对促进科研交流与合作、评审回避等有重要意义. 以论文合作网络为基础, 依据学生发表论文时通常与导师共同署名的现象, 抽象出能够反映导师-学生合作关系的特征, 提出了基于最大熵模型的导师-学生关系识别算法. 利用DBLP中1990-2011年的论文数据进行实例验证, 结果显示: 1)关系类型识别结果的准确率超过95%; 2)导师-学生关系终止时间的平均误差为1.39年. 该方法在识别关系时避免了特征之间相互独立的约束, 准确率优于其他同类识别算法, 且建模方法对识别社交网络中的其他关系类型也具有借鉴意义.

English Abstract

参考文献 (13)

目录

    /

    返回文章
    返回