
The core message of this paper is that the distortion of user similarity relationships across domains is a key factor causing negative transfer in cross-domain recommendation, and the proposed Collaborative information regularized User Transformation (CUT) framework can effectively alleviate this issue by directly filtering irrelevant source-domain collaborative information.


coremsg

collaborative-information-filtering-for-effective-cross-domain-recommendation


Collaborative Information Filtering for Effective Cross-Domain Recommendation


title_rewrite


Knowledge graphs are crucial for enhancing recommender systems, and the InBox model introduces a novel approach by utilizing interest box embedding to improve recommendation accuracy.


inbox-recommendation-with-knowledge-graph-using-interest-box-embedding


InBox: Recommendation with Knowledge Graph using Interest Box Embedding



The author introduces LiMAML, a meta-learning solution for personalizing deep recommender models, showcasing its superiority over traditional approaches through extensive experimentation and online deployment.


LiMAML-Personalization-of-Deep-Recommender-Models-via-Meta-Learning


LiMAML: Personalization of Deep Recommender Models via Meta Learning
