Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks

被引:0
|
作者
Schreurs, Joachim [1 ]
De Meulemeester, Hannes [1 ]
Fanuel, Michael [2 ]
De Moor, Bart [1 ]
Suykens, Johan A. K. [1 ]
机构
[1] Katholieke Univ Leuven, ESAT STADIUS, Kasteelpk Arenberg 10, B-3001 Leuven, Belgium
[2] Univ Lille, CNRS, Cent Lille, UMR 9189,CRIStAL, F-59000 Lille, France
基金
欧洲研究理事会;
关键词
GANs; Leverage score sampling; Complete mode coverage;
D O I
10.1007/978-3-030-95470-3_35
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Commonly, machine learning models minimize an empirical expectation. As a result, the trained models typically perform well for the majority of the data but the performance may deteriorate in less dense regions of the dataset. This issue also arises in generative modeling. A generative model may overlook underrepresented modes that are less frequent in the empirical data distribution. This problem is known as complete mode coverage. We propose a sampling procedure based on ridge leverage scores which significantly improves mode coverage when compared to standard methods and can easily be combined with any GAN. Ridge leverage scores are computed by using an explicit feature map, associated with the next-to-last layer of a GAN discriminator or of a pre-trained network, or by using an implicit feature map corresponding to a Gaussian kernel. Multiple evaluations against recent approaches of complete mode coverage show a clear improvement when using the proposed sampling strategy.
引用
收藏
页码:466 / 480
页数:15
相关论文
共 50 条
  • [21] Steganographic Generative Adversarial Networks
    Volkhonskiy, Denis
    Nazarov, Ivan
    Burnaev, Evgeny
    TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), 2020, 11433
  • [22] Wasserstein Generative Adversarial Networks
    Arjovsky, Martin
    Chintala, Soumith
    Bottou, Leon
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [23] Coevolution of Generative Adversarial Networks
    Costa, Victor
    Lourenco, Nuno
    Machado, Penousal
    APPLICATIONS OF EVOLUTIONARY COMPUTATION, EVOAPPLICATIONS 2019, 2019, 11454 : 473 - 487
  • [24] A survey of generative adversarial networks
    Zhu, Kongtao
    Liu, Xiwei
    Yang, Hongxue
    2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, : 2768 - 2773
  • [25] Triple Generative Adversarial Networks
    Li, Chongxuan
    Xu, Kun
    Zhu, Jun
    Liu, Jiashuo
    Zhang, Bo
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (12) : 9629 - 9640
  • [26] Stacked Generative Adversarial Networks
    Huang, Xun
    Li, Yixuan
    Poursaeed, Omid
    Hopcroft, John
    Belongie, Serge
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1866 - 1875
  • [27] Graphical Generative Adversarial Networks
    Li, Chongxuan
    Welling, Max
    Zhu, Jun
    Zhang, Bo
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [28] Triangle Generative Adversarial Networks
    Gan, Zhe
    Chen, Liqun
    Wang, Weiyao
    Pu, Yunchen
    Zhang, Yizhe
    Liu, Hao
    Li, Chunyuan
    Carin, Lawrence
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [29] Evolutionary Generative Adversarial Networks
    Wang, Chaoyue
    Xu, Chang
    Yao, Xin
    Tao, Dacheng
    IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2019, 23 (06) : 921 - 934
  • [30] A Review on Generative Adversarial Networks
    Yuan, Yiqin
    Guo, Yuhao
    2020 5TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE, COMPUTER TECHNOLOGY AND TRANSPORTATION (ISCTT 2020), 2020, : 392 - 401