On multiple-instance learning of halfspaces

被引:2
|
作者
Diochnos, D. I. [1 ]
Sloan, R. H. [1 ]
Turan, Gy [1 ,2 ,3 ]
机构
[1] Univ Illinois, Chicago, IL 60607 USA
[2] Hungarian Acad Sci, Res Grp AI, H-1051 Budapest, Hungary
[3] Univ Szeged, Szeged, Hungary
基金
美国国家科学基金会;
关键词
Machine learning; Halfspaces; Multiple-instance learning; Cyclic polytopes; PAC learning; VC-dimension; Combinatorial problems;
D O I
10.1016/j.ipl.2012.08.017
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In multiple-instance learning the learner receives bags, i.e., sets of instances. A bag is labeled positive if it contains a positive example of the target. An Omega(d logr) lower bound is given for the VC-dimension of bags of size r for d-dimensional halfspaces and it is shown that the same lower bound holds for halfspaces over any large point set in general position. This lower bound improves an Omega(logr) lower bound of Sabato and Tishby, and it is sharp in order of magnitude. We also show that the hypothesis finding problem is NP-complete and formulate several open problems. (C) 2012 Elsevier B.V. All rights reserved.
引用
收藏
页码:933 / 936
页数:4
相关论文
共 50 条
  • [1] Compact Multiple-Instance Learning
    Chai, Jing
    Liu, Weiwei
    Tsang, Ivor W.
    Shen, Xiaobo
    [J]. CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, : 2007 - 2010
  • [2] ON GENERALIZED MULTIPLE-INSTANCE LEARNING
    Scott, Stephen
    Zhang, Jun
    Brown, Joshua
    [J]. INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2005, 5 (01) : 21 - 35
  • [3] A framework for multiple-instance learning
    Maron, O
    Lozano-Perez, T
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 10, 1998, 10 : 570 - 576
  • [4] UNSUPERVISED MULTIPLE-INSTANCE LEARNING FOR INSTANCE SEARCH
    Wang, Zhenzhen
    Yuan, Junsong
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2018,
  • [5] MULTIPLE-INSTANCE LEARNING WITH PAIRWISE INSTANCE SIMILARITY
    Yuan, Liming
    Liu, Jiafeng
    Tang, Xianglong
    [J]. INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2014, 24 (03) : 567 - 577
  • [6] Salient Instance Selection for Multiple-Instance Learning
    Yuan, Liming
    Liu, Songbo
    Huang, Qingcheng
    Liu, Jiafeng
    Tang, Xianglong
    [J]. NEURAL INFORMATION PROCESSING, ICONIP 2012, PT III, 2012, 7665 : 58 - 67
  • [7] Kernels for Generalized Multiple-Instance Learning
    Tao, Qingping
    Scott, Stephen D.
    Vinodchandran, N. V.
    Osugi, Thomas Takeo
    Mueller, Brandon
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2008, 30 (12) : 2084 - 2097
  • [8] Multiple-Instance Learning from Distributions
    Doran, Gary
    Ray, Soumya
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2016, 17
  • [9] An improved multiple-instance learning algorithm
    Han, Fengqing
    Wang, Dacheng
    Liao, Xiaofeng
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 1, PROCEEDINGS, 2007, 4491 : 1104 - +
  • [10] Saliency Detection by Multiple-Instance Learning
    Wang, Qi
    Yuan, Yuan
    Yan, Pingkun
    Li, Xuelong
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2013, 43 (02) : 660 - 672