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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the information age, recommendation systems are vital for efficientlyfiltering information and identifying user preferences. Online social platformshave enriched these systems by providing valuable auxiliary information.Socially connected users are assumed to share similar preferences, enhancingrecommendation accuracy and addressing cold start issues. However, empiricalfindings challenge the assumption, revealing that certain social connectionscan actually harm system performance. Our statistical analysis indicates asignificant amount of noise in the social network, where many sociallyconnected users do not share common interests. To address this issue, wepropose an innovative \underline{I}nterest-aware \underline{D}enoising and\underline{V}iew-guided \underline{T}uning (IDVT) method for the socialrecommendation. The first ID part effectively denoises social connections.Specifically, the denoising process considers both social network structure anduser interaction interests in a global view. Moreover, in this global view, wealso integrate denoised social information (social domain) into the propagationof the user-item interactions (collaborative domain) and aggregate userrepresentations from two domains using a gating mechanism. To tackle potentialuser interest loss and enhance model robustness within the global view, oursecond VT part introduces two additional views (local view and dropout-enhancedview) for fine-tuning user representations in the global view throughcontrastive learning. Extensive evaluations on real-world datasets with varyingnoise ratios demonstrate the superiority of IDVT over state-of-the-art socialrecommendation methods.

IDVT: Interest-aware Denoising and View-guided Tuning for Social Recommendation