Crossmark

Personalized design aesthetic preference modeling: a variational autoencoder and meta-learning approach for multi-modal feature representation and transfer optimization

Crossref DOI link: https://doi.org/10.1038/s41598-025-26269-6

Published Online: 2025-11-24

Update policy: https://doi.org/10.1007/springer_crossmark_policy

Authors

Chen, Chengliang

Gong, Zhiqun
License Information

Text and Data Mining valid from 2025-11-24

Version of Record valid from 2025-11-24
More Information

Article History

Received: 24 August 2025

Accepted: 28 October 2025

First Online: 24 November 2025

Declarations

:

: This study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Dankook University (IRB approval number: DKU-2024-08-015). Written informed consent was obtained from all participants involved in the aesthetic preference annotation process. The study involved only non-invasive data collection through design preference ratings and behavioral interaction logging, posing minimal risk to participants.

: The authors declare no competing interests.

Document is current

Any future updates will be listed below