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

Collaborative Filtering (CF) is a pivotal research area in recommendersystems that capitalizes on collaborative similarities between users and itemsto provide personalized recommendations. With the remarkable achievements ofnode embedding-based Graph Neural Networks (GNNs), we explore the upper boundsof expressiveness inherent to embedding-based methodologies and tackle thechallenges by reframing the CF task as a graph signal processing problem. Tothis end, we propose PolyCF, a flexible graph signal filter that leveragespolynomial graph filters to process interaction signals. PolyCF exhibits thecapability to capture spectral features across multiple eigenspaces through aseries of Generalized Gram filters and is able to approximate the optimalpolynomial response function for recovering missing interactions. A graphoptimization objective and a pair-wise ranking objective are jointly used tooptimize the parameters of the convolution kernel. Experiments on three widelyadopted datasets demonstrate the superiority of PolyCF over currentstate-of-the-art CF methods. Moreover, comprehensive studies empiricallyvalidate each component's efficacy in the proposed PolyCF.

PolyCF: Towards the Optimal Spectral Graph Filters for Collaborative Filtering