Semi-supervised Sequential Generative Models

被引:0
|
作者
Teng, Michael [1 ]
Le, Tuan Anh [2 ]
Scibior, Adam [3 ]
Wood, Frank [3 ,4 ]
机构
[1] Univ Oxford, Dept Engn Sci, Oxford, England
[2] MIT, Dept Brain & Cognit Sci, Cambridge, MA 02139 USA
[3] Univ British Columbia, Dept Comp Sci, Vancouver, BC, Canada
[4] Montreal Inst Learning Algorithms MILA, Montreal, PQ, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce a novel objective for training deep generative time-series models with discrete latent variables for which supervision is only sparsely available. This instance of semi-supervised learning is challenging for existing methods, because the exponential number of possible discrete latent configurations results in high variance gradient estimators. We first overcome this problem by extending the standard semi-supervised generative modeling objective with reweighted wake-sleep. However, we find that this approach still suffers when the frequency of available labels varies between training sequences. Finally, we introduce a unified objective inspired by teacher-forcing and show that this approach is robust to variable length supervision. We call the resulting method caffeinated wake-sleep (CWS) to emphasize its additional dependence on real data. We demonstrate its effectiveness with experiments on MNIST, handwriting, and fruit fly trajectory data.
引用
收藏
页码:649 / 658
页数:10
相关论文
共 50 条
  • [31] Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks
    Diaz-Frances, Jose Angel
    Fernandez-Rodriguez, Jose David
    Thurnhofer-Hemsi, Karl
    Lopez-Rubio, Ezequiel
    [J]. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2024, 34 (11)
  • [32] Bi-Modality Medical Image Synthesis Using Semi-Supervised Sequential Generative Adversarial Networks
    Yang, Xin
    Lin, Yi
    Wang, Zhiwei
    Li, Xin
    Cheng, Kwang-Ting
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (03) : 855 - 865
  • [33] Semi-Supervised Multi-Label Learning from Crowds via Deep Sequential Generative Model
    Shi, Wanli
    Sheng, Victor S.
    Li, Xiang
    Gu, Bin
    [J]. KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 1141 - 1149
  • [34] Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization
    Li, Daiqing
    Yang, Junlin
    Kreis, Karsten
    Torralba, Antonio
    Fidler, Sanja
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 8296 - 8307
  • [35] Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
    Zhu, Yi
    Shareghi, Ehsan
    Li, Yingzhen
    Reichart, Roi
    Korhonen, Anna
    [J]. 16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 894 - 908
  • [36] Semi-supervised COVID-19 CT image segmentation using deep generative models
    Judah Zammit
    Daryl L. X. Fung
    Qian Liu
    Carson Kai-Sang Leung
    Pingzhao Hu
    [J]. BMC Bioinformatics, 23
  • [37] SEMI-SUPERVISED LEARNING BASED ON HIERARCHICAL GENERATIVE MODELS FOR END-TO-END SPEECH SYNTHESIS
    Fujimoto, Takato
    Takaki, Shinji
    Hashimoto, Kei
    Oura, Keiichiro
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 7644 - 7648
  • [38] Semi-supervised COVID-19 CT image segmentation using deep generative models
    Zammit, Judah
    Fung, Daryl L. X.
    Liu, Qian
    Leung, Carson Kai-Sang
    Hu, Pingzhao
    [J]. BMC BIOINFORMATICS, 2022, 23 (SUPPL 7)
  • [39] Semi-Supervised Generative Adversarial Network for Gene Expression Inference
    Dizaji, Kamran Ghasedi
    Wang, Xiaoqian
    Huang, Heng
    [J]. KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 1435 - 1444
  • [40] Event Representation with Sequential, Semi-Supervised Discrete Variables
    Rezaee, Mehdi
    Ferraro, Francis
    [J]. 2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 4701 - 4716