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
  • [21] A hybrid generative/discriminative method for semi-supervised classification
    Jiang, Zhen
    Zhang, Shiyong
    Zeng, Jianping
    [J]. KNOWLEDGE-BASED SYSTEMS, 2013, 37 : 137 - 145
  • [22] Semi-supervised Seizure Prediction with Generative Adversarial Networks
    Nhan Duy Truong
    Zhou, Luping
    Kavehei, Omid
    [J]. 2019 41ST ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2019, : 2369 - 2372
  • [23] Generative adversarial network for semi-supervised image captioning
    Liang, Xu
    Li, Chen
    Tian, Lihua
    [J]. Computer Vision and Image Understanding, 2024, 249
  • [24] A Generative Semi-Supervised Classifier for Datasets with Unknown Classes
    Schrunner, Stefan
    Geiger, Bernhard C.
    Zernig, Anja
    Kern, Roman
    [J]. PROCEEDINGS OF THE 35TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING (SAC'20), 2020, : 1066 - 1074
  • [25] SEMI-SUPERVISED SOURCE LOCALIZATION WITH DEEP GENERATIVE MODELING
    Bianco, Michael J.
    Gannot, Sharon
    Gerstoft, Peter
    [J]. PROCEEDINGS OF THE 2020 IEEE 30TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2020,
  • [26] Semi-supervised Learning Using Generative Adversarial Networks
    Chang, Chuan-Yu
    Chen, Tzu-Yang
    Chung, Pau-Choo
    [J]. 2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 892 - 896
  • [27] Semi-Supervised Learning with Coevolutionary Generative Adversarial Networks
    Toutouh, Jamal
    Nalluru, Subhash
    Hemberg, Erik
    O'Reilly, Una-May
    [J]. PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2023, 2023, : 568 - 576
  • [28] Semi-supervised Learning on Graphs with Generative Adversarial Nets
    Ding, Ming
    Tang, Jie
    Zhang, Jie
    [J]. CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, : 913 - 922
  • [29] Semi-supervised Generative Adversarial Hashing for Image Retrieval
    Wang, Guan'an
    Hu, Qinghao
    Cheng, Jian
    Hou, Zengguang
    [J]. COMPUTER VISION - ECCV 2018, PT 15, 2018, 11219 : 491 - 507
  • [30] Semi-Supervised Dose Prediction with Generative Adversarial Learning
    Lam, D.
    Sun, B.
    [J]. MEDICAL PHYSICS, 2019, 46 (06) : E418 - E418