A Commentary on the Unsupervised Learning of Disentangled Representations

被引：0

作者：

Locatello, Francesco ^{[2
,3
]}

Bauer, Stefan ^{[3
]}

Lucie, Mario ^{[1
]}

Raetsch, Gunnar ^{[2
]}

Gelly, Sylvain ^{[1
]}

Schoelkopf, Bernhard ^{[3
]}

Bachem, Olivier ^{[1
]}

机构：

[1] Google Res, Mountain View, CA 94043 USA

[2] Swiss Fed Inst Technol, Dept Comp Sci, Zurich, Switzerland

[3] Max Planck Inst Intelligent Syst, Stuttgart, Germany

来源：

THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2020年 / 34卷

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：

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In this paper, we summarize the results of (Locatello et al. 2019b) and focus on their implications for practitioners. We discuss the theoretical result showing that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases and the practical challenges it entails. Finally, we comment on our experimental findings, highlighting the limitations of state-of-the-art approaches and directions for future research.

引用

页码：13681 / 13684

页数：4

共 50 条

[1] Unsupervised Learning of Disentangled Representations from Video
Denton, Emily
Birodkar, Vighnesh
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[2] A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
Locatello, Francesco
Bauer, Stefan
Lucic, Mario
Ratsch, Gunnar
Gelly, Sylvain
Schoelkopf, Bernhard
Bachem, Olivier
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
[3] Independent Subspace Analysis for Unsupervised Learning of Disentangled Representations
Stuhmer, Jan
Turner, Richard E.
Nowozin, Sebastian
[J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108
[4] Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Locatello, Francesco
Bauer, Stefan
Lucic, Mario
Ratsch, Gunnar
Gelly, Sylvain
Scholkopf, Bernhard
Bachem, Olivier
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[5] Geometric Inductive Biases for Identifiable Unsupervised Learning of Disentangled Representations
Pan, Ziqi
Niu, Li
Zhang, Liqing
[J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 8, 2023, : 9372 - 9380
[6] Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
Hsu, Wei-Ning
Zhang, Yu
Glass, James
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[7] Linear Disentangled Representations and Unsupervised Action Estimation
Painter, Matthew
Hare, Jonathon
Prugel-Bennett, Adam
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[8] Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory
Zuo, Lianrui
Dewey, Blake E.
Liu, Yihao
He, Yufan
Newsome, Scott D.
Mowry, Ellen M.
Resnick, Susan M.
Prince, Jerry L.
Carass, Aaron
[J]. NEUROIMAGE, 2021, 243
[9] Unsupervised learning of disentangled representations in deep restricted kernel machines with orthogonality constraints
Tonin, Francesco
Patrinos, Panagiotis
Suykens, Johan A. K.
[J]. NEURAL NETWORKS, 2021, 142 : 661 - 679
[10] Learning Disentangled Representations for Recommendation
Ma, Jianxin
Zhou, Chang
Cui, Peng
Yang, Hongxia
Zhu, Wenwu
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32

← 1 2 3 4 5 →