Disentangled Representation Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9677-9696
DOI: 10.1109/tpami.2024.3420937 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Xin Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 183-mal zitiert (Crossref) und nennt 142 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Beijing National Research Center for Information Science and Technology.
Abstract (Originalsprache)
Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form. The process of separating underlying factors of variation into variables with semantic meaning benefits in learning explainable representations of data, which imitates the meaningful understanding process of humans when observing an object or relation. As a general learning strategy, DRL has demonstrated its power in improving the model explainability, controlability, robustness, as well as generalization capacity in a wide range of scenarios such as computer vision, natural language processing, and data mining. In this article, we comprehensively investigate DRL from various aspects including motivations, definitions, methodologies, evaluations, applications, and model designs. We first present two well-recognized definitions, i.e., Intuitive Definition and Group Theory Definition for disentangled representation learning. We further categorize the methodologies for DRL into four groups from the following perspectives, the model type, representation structure, supervision signal, and independence assumption. We also analyze principles to design different DRL models that may benefit different tasks in practical applications. Finally, we point out challenges in DRL as well as potential research directions deserving future investigations. We believe this work may provide insights for promoting the DRL research in the community.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Beijing National Research Center for Information Science and Technology
- Beijing Key Lab of Networked Multimedia
Zitieren
APA
Wang, X., Chen, H., Tang, S., Wu, Z., & Zhu, W. (2024). Disentangled Representation Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9677-9696. https://doi.org/10.1109/tpami.2024.3420937
Vancouver
Wang X, Chen H, Tang S, Wu Z, Zhu W. Disentangled Representation Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9677-9696. doi:10.1109/tpami.2024.3420937
BibTeX
@article{Wang2024,
author = {Wang, Xin and Chen, Hong and Tang, Si'ao and Wu, Zihao and Zhu, Wenwu},
title = {Disentangled Representation Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {9677--9696},
doi = {10.1109/tpami.2024.3420937}
}
EUVIMED