Self-attention Multi-view Representation Learning with Diversity-promoting Complementarity

被引:0
|
作者
Liu, Jian-wei [1 ]
Ding, Xi-hao [1 ]
Lu, Run-kun [1 ]
Luo, Xionglin [1 ]
机构
[1] China Univ Petr, Sch Informat Sci & Engn, Dept Automat, Beijing 102249, Peoples R China
关键词
Multi-view Learning; Self-attention Mechanism; Complementary Information with Diversity;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Multi-view learning attempts to generate a model with a better performance by exploiting the consensus and/or complementarity among multi-view data. However, in terms of complementarity, most existing approaches only can find representations with single complementarity rather than complementary information with diversity. In this paper, to utilize both complementarity and consistency simultaneously, give free rein to the potential of deep learning in grasping diversity-promoting complementarity for multi-view representation learning, we propose a novel supervised multi-view representation learning algorithm, called Self-Attention Multi-View network with Diversity-Promoting Complementarity (SAMVDPC), which exploits the consistency by a group of encoders, uses self-attention to find complementary information entailing diversity. Extensive experiments conducted on eight real-world datasets have demonstrated the effectiveness of our proposed method, and show its superiority over several baseline methods, which only consider single complementary information.
引用
收藏
页码:3972 / 3978
页数:7
相关论文
共 50 条
  • [21] Self-attention with Functional Time Representation Learning
    Xu, Da
    Ruan, Chuanwei
    Kumar, Sushant
    Korpeoglu, Evren
    Achan, Kannan
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [22] An Attention-based Collaboration Framework for Multi-View Network Representation Learning
    Qu, Meng
    Tang, Jian
    Shang, Jingbo
    Ren, Xiang
    Zhang, Ming
    Han, Jiawei
    [J]. CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, : 1767 - 1776
  • [23] Improved Multi-Head Self-Attention Classification Network for Multi-View Fetal Echocardiography Recognition
    Zhang, Yingying
    Zhu, Haogang
    Wang, Yan
    Wang, Jingyi
    He, Yihua
    [J]. 2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,
  • [24] SC2-Net: Self-supervised learning for multi-view complementarity representation and consistency fusion network
    Huang, Liting
    Fan, Xiangyang
    Xia, Tianlin
    Li, Yuhang
    Ding, Youdong
    [J]. NEUROCOMPUTING, 2023, 556
  • [25] Self Supervised Multi-view Graph Representation Learning in Digital Pathology
    Ramanathan, Vishwesh
    Martel, Anne L.
    [J]. GRAPHS IN BIOMEDICAL IMAGE ANALYSIS, AND OVERLAPPED CELL ON TISSUE DATASET FOR HISTOPATHOLOGY, 5TH MICCAI WORKSHOP, 2024, 14373 : 74 - 84
  • [26] MHSAN: Multi-view hierarchical self-attention network for 3D shape recognition
    Cao, Jiangzhong
    Yu, Lianggeng
    Ling, Bingo Wing-Kuen
    Yao, Zijie
    Dai, Qingyun
    [J]. PATTERN RECOGNITION, 2024, 150
  • [27] DEEP MULTI-VIEW ROBUST REPRESENTATION LEARNING
    Jiao, Zhenyu
    Xu, Chao
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 2851 - 2855
  • [28] Multi-View Concept Learning for Data Representation
    Guan, Ziyu
    Zhang, Lijun
    Peng, Jinye
    Fan, Jianping
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2015, 27 (11) : 3016 - 3028
  • [29] Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning
    Li, Bing
    Yuan, Chunfeng
    Xiong, Weihua
    Hu, Weiming
    Peng, Houwen
    Ding, Xinmiao
    Maybank, Steve
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (12) : 2554 - 2560
  • [30] Unsupervised Multi-View Gaze Representation Learning
    Gideon, John
    Su, Shan
    Stent, Simon
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 4997 - 5005