References & Citations
Computer Science > Machine Learning
Title: Disentangled Representation Learning
(Submitted on 21 Nov 2022 (v1), last revised 2 May 2024 (this version, v3))
Abstract: 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.
Submission history
From: Xin Wang [view email][v1] Mon, 21 Nov 2022 18:14:38 GMT (2611kb,D)
[v2] Wed, 16 Aug 2023 16:05:00 GMT (2110kb,D)
[v3] Thu, 2 May 2024 16:28:43 GMT (2981kb,D)
Link back to: arXiv, form interface, contact.