Disentangled Representation Learning for Multimedia
Open Access
- 26 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 9702-9704
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, controllability, robustness, as well as generalization capacity in a wide range of scenarios such as computer vision, natural language processing, data mining etc. In this tutorial, we comprehensively present DRL from various aspects including motivations, definitions, methodologies, evaluations, applications and model designs for multimedia. We discuss works on DRL based on two well-recognized definitions, i.e., Intuitive Definition and Group Theory Definition. We further categorize the methodologies for DRL into four groups, i.e., Traditional Statistical Approaches, Variational Auto-encoder Based Approaches, Generative Adversarial Networks Based Approaches, Hierarchical Approaches and Other Approaches. We also analyze principles to design different DRL models that may benefit different tasks in practical multimedia applications. Finally, we point out challenges in DRL as well as potential research directions deserving future investigations. We believe this tutorial may provide insights for promoting the DRL research in the multimedia community.Keywords
Funding Information
- National Key Research and Development Program of China (2020AAA0106300)
- National Natural Science Foundation of China (62222209, 62250008, 62102222)
- Beijing National Research Center For Information Science And Technology (BNR2023RC01003, BNR2023TD03006)
This publication has 11 references indexed in Scilit:
- Video Grounding and Its Generalization2022
- Disentangled Graph Contrastive Learning With Independence PromotionIEEE Transactions on Knowledge and Data Engineering, 2022
- Out-of-distribution Generalization and Its Applications for Multimedia2021
- Automated Machine Learning on Graph2021
- Automated Machine Learning on Graphs: A Survey2021
- Multimodal Disentangled Representation for Recommendation2021
- A Survey on Curriculum LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Multimedia Intelligence: When Multimedia Meets Artificial Intelligence2020
- Disentangled Self-Supervision in Sequential Recommenders2020
- AutoML and Meta-learning for Multimedia2019