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/

Global: Zendy Tools annual

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

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Cross-domain Recommendation (CR) is the task that tends to improve therecommendations in the sparse target domain by leveraging the information fromother rich domains. Existing methods of cross-domain recommendation mainlyfocus on overlapping scenarios by assuming users are totally or partiallyoverlapped, which are taken as bridges to connect different domains. However,this assumption does not always hold since it is illegal to leak users'identity information to other domains. Conducting Non-overlapping MCR (NMCR) ischallenging since 1) The absence of overlapping information prevents us fromdirectly aligning different domains, and this situation may get worse in theMCR scenario. 2) The distribution between source and target domains makes itdifficult for us to learn common information across domains. To overcome theabove challenges, we focus on NMCR, and devise MCRPL as our solution. Toaddress Challenge 1, we first learn shared domain-agnostic and domain-dependentprompts, and pre-train them in the pre-training stage. To address Challenge 2,we further update the domain-dependent prompts with other parameters kept fixedto transfer the domain knowledge to the target domain. We conduct experimentson five real-world domains, and the results show the advance of our MCRPLmethod compared with several recent SOTA baselines.

MCRPL: A Pretrain, Prompt & Fine-tune Paradigm for Non-overlapping Many-to-one Cross-domain Recommendation