Disentangling multi-view representations beyond inductive bias
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...
Saved in:
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: | |
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 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Disentangled Graph Collaborative Filtering
by: WANG XIANG, et al.
Published: (2020) -
Aligning dual disentangled user representations from ratings and textual content
by: TRAN, Nhu Thuat, et al.
Published: (2022) -
ALGORITHMIC INDUCTIVE BIASES FOR GRAPH REPRESENTATION LEARNING
by: MOHAMMED HAROON DUPTY
Published: (2022) -
EAD-GAN: a generative adversarial network for disentangling affine transforms in images
by: Liu, Letao, et al.
Published: (2023) -
Surgical activity triplet recognition via triplet disentanglement
by: CHEN, Yiliang, et al.
Published: (2023)