A Review of Disentangled Representation Learning

被引：0
|
作者：
Wen Z.-D. [1 ,2 ]
Wang J.-R. [1 ,2 ]
Wang X.-X. [1 ,2 ]
Pan Q. [1 ,2 ]
机构：
[1] School of Automation, Northwestern Polytechnical University, Xi'an
[2] Key Laboratory of Information Fusion Technology, Ministry of Education, Xi'an
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2022年 / 48卷 / 02期
基金：
中国国家自然科学基金;
关键词：
Deep learning; Disentangled representation learning; Generative latent factors; Intelligent perception; Shortcut learning;
D O I：
10.16383/j.aas.c210096
中图分类号：
学科分类号：
摘要：
In the era of big data, deep learning has triggered the current rise of artificial intelligence which is known for its ability of efficient autonomous implicit feature extraction. However, the unexplainable "shortcut learning" phenomenon behind it has become a key bottleneck restricting its further development. By exploring the complexity of physical mechanism and logical relationship contained in big data, the disentangled representation learning aims to explore the multi-level and multi-scale explanatory generative latent factors behind the data, and prompts the deep neural network model to learn the ability of intelligent human perception. It has gradually become an important research direction in the field of deep learning, with huge theoretical significance and application value. This article systematically reviews the research of disentangled representation learning, classifies and elaborates state-of-the-art algorithms in disentangled representation learning, summarizes the applications of the existing algorithms and compares the performance of existing algorithms through experiments. Finally, the challenges and research trends in the field of disentangled representation learning are discussed. Copyright ©2019 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：351 / 374
页数：23
相关论文
共 131 条
  • [1] Duan Yan-Jie, Lv Yi-Sheng, Zhang Jie, Zhao Xue-Liang, Wang Fei-Yue, Deep learning for control: The state of the art and prospects, Acta Automatica Sinica, 42, 5, pp. 634-654, (2016)
  • [2] Wang Xiao-Feng, Yang Ya-Dong, Research on structure model of general intelligent system based on ecological evolution, Acta Automatica Sinica, 46, 5, pp. 1017-1030, (2020)
  • [3] Amizadeh S, Palangi H, Polozov O, Huang Y C, Koishida K., Neuro-Symbolic visual reasoning: Disentangling "visual" from "reasoning, Proceedings of the 37th International Conference on Machine Learning, pp. 279-290, (2020)
  • [4] Adel T, Zhao H, Turner R E., Continual learning with adaptive weights (CLAW), Proceedings of the 8th International Conference on Learning Representations, (2020)
  • [5] Hinton G E, Salakhutdinov R R., Reducing the dimensionality of data with neural networks, Science, 313, 5786, (2006)
  • [6] Lee G, Li H Z., Modeling code-switch languages using bilingual parallel corpus, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 860-870, (2020)
  • [7] Chen X H., Simulation of English speech emotion recognition based on transfer learning and CNN neural network, Journal of Intelligent & Fuzzy Systems, 40, 2, pp. 2349-2360, (2021)
  • [8] Lu Y, Lin H, Wu P P, Chen Y T., Feature compensation based on independent noise estimation for robust speech recognition, EURASIP Journal on Audio, Speech, and Music Processing, 2021, 1, (2021)
  • [9] Torfi A, Shirvani R A, Keneshloo Y, Tavaf N, Fox E A., Natural language processing advancements by deep learning: A survey, (2020)
  • [10] Stoll S, Camgoz N C, Hadfield S, Bowden R., Text2Sign: Towards sign language production using neural machine translation and generative adversarial networks, International Journal of Computer Vision, 128, 4, pp. 891-908, (2020)
12345678910