Self-Training of Graph Neural Networks Using Similarity Reference for Robust Training with Noisy Labels

被引：0
|
作者：
Park, Hyoungseob [1 ]
Jeong, Minki [1 ]
Kim, Youngeun [1 ]
Kim, Changick [1 ]
机构：
[1] Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, Republic of
来源：
Proceedings - International Conference on Image Processing, ICIP | 2020年 / 2020-October卷
关键词：
Fundamental limitations - Graph neural networks - Graph-based learning - Label information - Robust trainings - Sampling method - State of the art - Training data;
D O I：
9191054
中图分类号：
学科分类号：
摘要：
21
引用
收藏
页码：1951 / 1955
相关论文
共 50 条
  • [21] Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
    Zhang, Zhilu
    Sabuncu, Mert R.
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [22] Crafting networks: A self-training intervention
    Wang, Huatian
    Demerouti, Evangelia
    Rispens, Sonja
    van Gool, Piet
    [J]. JOURNAL OF VOCATIONAL BEHAVIOR, 2024, 149
  • [23] Graph-Based Self-Training for Semi-Supervised Deep Similarity Learning
    Wang, Yifan
    Huang, Yan
    Wang, Qicong
    Zhao, Chong
    Zhang, Zhenchang
    Chen, Jian
    [J]. SENSORS, 2023, 23 (08)
  • [24] SELF-TRAINING ARTIFICIAL NEURAL NETWORKS - A NEW METHOD FOR DETECTING ARRHYTHMIA
    EVANS, SJ
    HASTINGS, H
    BODENHEIMER, MM
    [J]. CIRCULATION, 1992, 86 (04) : 857 - 857
  • [25] NOISY TRAINING FOR DEEP NEURAL NETWORKS
    Meng, Xiangtao
    Liu, Chao
    Zhang, Zhiyong
    Wang, Dong
    [J]. 2014 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (CHINASIP), 2014, : 16 - 20
  • [26] Training Neural Networks on Noisy Data
    Rusiecki, Andrzej
    Kordos, Miroslaw
    Kaminski, Tomasz
    Gren, Krzysztof
    [J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING ICAISC 2014, PT I, 2014, 8467 : 131 - 142
  • [27] DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels
    Olimov, Bekhzod
    Kim, Jeonghong
    Paul, Anand
    [J]. IEEE ACCESS, 2020, 8 : 220482 - 220495
  • [28] A Study on the Impact of Data Augmentation for Training Convolutional Neural Networks in the Presence of Noisy Labels
    Pereira, Emeson
    Carneiro, Gustavo
    Cordeiro, Filipe R.
    [J]. 2022 35TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2022), 2022, : 25 - 30
  • [29] Neighborhood-Regularized Self-Training for Learning with Few Labels
    Xu, Ran
    Yu, Yue
    Cui, Hejie
    Kan, Xuan
    Zhu, Yanqiao
    Ho, Joyce
    Zhang, Chao
    Yang, Carl
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 9, 2023, : 10611 - 10619
  • [30] Robust Loss Functions for Training Decision Trees with Noisy Labels
    Wilton, Jonathan
    Ye, Nan
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 14, 2024, : 15859 - 15867
12345