A Novel Random Forest Dissimilarity Measure for Multi-View Learning

被引:3
|
作者
Cao, Hongliu [1 ,2 ]
Bernard, Simon [1 ]
Sabourin, Robert [2 ]
Heutte, Laurent [1 ]
机构
[1] Univ Rouen Normandie, LITIS, F-76000 Rouen, France
[2] Univ Quebec, Ecole Technol Super ETS, LIVIA, Montreal, PQ, Canada
关键词
Multi-view learning; Dissimilarity Representation; Random Forest; High Dimension Low Sample Size;
D O I
10.1109/ICPR48806.2021.9412961
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-view learning is a learning task in which data is described by several concurrent representations. Its main challenge is most often to exploit the complementarities between these representations to help solve a classification/regression task. This is a challenge that can be met nowadays if there is a large amount of data available for learning. However, this is not necessarily true for all real-world problems, where data are sometimes scarce (e.g. problems related to the medical environment). In these situations, an effective strategy is to use intermediate representations based on the dissimilarities between instances. This work presents new ways of constructing these dissimilarity representations, learning them from data with Random Forest classifiers. More precisely, two methods are proposed, which modify the Random Forest proximity measure, to adapt it to the context of High Dimension Low Sample Size (HDLSS) multi-view classification problems. The second method, based on an Instance Hardness measurement, is significantly more accurate than other state-of-the-art measurements including the original RF Proximity measurement and the Large Margin Nearest Neighbor (LMNN) metric learning measurement.
引用
收藏
页码:1344 / 1351
页数:8
相关论文
共 50 条
  • [21] A Novel Regularization Learning for Single-View Patterns: Multi-View Discriminative Regularization
    Wang, Zhe
    Chen, Songcan
    Xue, Hui
    Pan, Zhisong
    [J]. NEURAL PROCESSING LETTERS, 2010, 31 (03) : 159 - 175
  • [22] Decoupled representation for multi-view learning
    Sun, Shiding
    Wang, Bo
    Tian, Yingjie
    [J]. PATTERN RECOGNITION, 2024, 151
  • [23] Multi-view representation learning and understanding
    [J]. Multimedia Tools and Applications, 2021, 80 : 22865 - 22865
  • [24] Uniform Projection for Multi-View Learning
    Zhang, Zhenyue
    Zhai, Zheng
    Li, Limin
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (08) : 1675 - 1689
  • [25] Unbalanced Multi-view Deep Learning
    Xu, Cai
    Li, Zehui
    Guan, Ziyu
    Zhao, Wei
    Song, Xiangyu
    Wu, Yue
    Li, Jianxin
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 3051 - 3059
  • [26] Incorporate Hashing with Multi-view Learning
    Tang, Jingjing
    Li, Dewei
    [J]. 2016 IEEE 16TH INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW), 2016, : 853 - 859
  • [27] Multi-view discriminative sequential learning
    Brefeld, U
    Büscher, C
    Scheffer, T
    [J]. MACHINE LEARNING: ECML 2005, PROCEEDINGS, 2005, 3720 : 60 - 71
  • [28] Multi-view Transfer Learning with Adaboost
    Xu, Zhijie
    Sun, Shiliang
    [J]. 2011 23RD IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2011), 2011, : 399 - 402
  • [29] Deep Multi-View Concept Learning
    Xu, Cai
    Guan, Ziyu
    Zhao, Wei
    Niu, Yunfei
    Wang, Quan
    Wang, Zhiheng
    [J]. PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 2898 - 2904
  • [30] Reliable Conflictive Multi-View Learning
    Xu, Cai
    Si, Jiajun
    Guan, Ziyu
    Zhao, Wei
    Wu, Yue
    Gao, Xiyue
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 14, 2024, : 16129 - 16137