Disentangled Representations Learning for Multi-target Cross-domain Recommendation.

Autor: XIAOBO GUO, SHAOSHUAI LI, NAICHENG GUO, JIANGXIA CAO, XIAOLEI LIU, QIONGXU MA, RUNSHENG GAN, YUNAN ZHAO
Zdroj: ACM Transactions on Information Systems; Oct2023, Vol. 41 Issue 4, p1-27, 27p
Abstrakt: The article focuses on addressing data sparsity in recommendation systems through multi-target cross-domain recommendation (CDR). It introduces DR-MTCDR, a novel model that efficiently disentangles domain-specific and domain-shared information to enhance recommendation performance across multiple domains, offering a solution to challenges posed by pairwise transferring methods.
Databáze: Complementary Index