Disentangling multi-view representations beyond inductive bias

• Main Authors: KE, Guanzhou, YU, Yang, CHAO, Guoqing, WANG, Xiaoli, XU, Chenyang, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Multi-view representation learning; Disentangled representation; Consistency and specificity; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8420; https://ink.library.smu.edu.sg/context/sis_research/article/9423/viewcontent/Disentangling_Multi_view_Representations_Beyond_Inductive_Bias.pdf
• Institution: Singapore Management University

Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by introducing strong inductive biases, which can limit their gener...