English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Pre-trained recommendation models (PRMs) have received increasing interestrecently. However, their intrinsically heterogeneous model structure, hugemodel size and computation cost hinder their adoptions in practical recommendersystems. Hence, it is highly essential to explore how to use differentpre-trained recommendation models efficiently in real-world systems. In thispaper, we propose a novel curriculum-scheduled knowledge distillation frommultiple pre-trained teachers for multi-domain sequential recommendation,called CKD-MDSR, which takes full advantages of different PRMs as multipleteacher models to boost a small student recommendation model, integrating theknowledge across multiple domains from PRMs. Specifically, CKD-MDSR firstadopts curriculum-scheduled user behavior sequence sampling and distillsinformative knowledge jointly from the representative PRMs such as UniSRec andRecformer. Then, the knowledge from the above PRMs are selectively integratedinto the student model in consideration of their confidence and consistency.Finally, we verify the proposed method on multi-domain sequentialrecommendation and further demonstrate its universality with multiple types ofstudent models, including feature interaction and graph based recommendationmodels. Extensive experiments on five real-world datasets demonstrate theeffectiveness and efficiency of CKD-MDSR, which can be viewed as an efficientshortcut using PRMs in real-world systems.

Curriculum-scheduled Knowledge Distillation from Multiple Pre-trained Teachers for Multi-domain Sequential Recommendation