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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The sequential recommendation system has been widely studied for itspromising effectiveness in capturing dynamic preferences buried in users'sequential behaviors. Despite the considerable achievements, existing methodsusually focus on intra-sequence modeling while overlooking exploiting globalcollaborative information by inter-sequence modeling, resulting in inferiorrecommendation performance. Therefore, previous works attempt to tackle thisproblem with a global collaborative item graph constructed by pre-definedrules. However, these methods neglect two crucial properties when capturingglobal collaborative information, i.e., adaptiveness and personalization,yielding sub-optimal user representations. To this end, we propose agraph-driven framework, named Adaptive and Personalized Graph Learning forSequential Recommendation (APGL4SR), that incorporates adaptive andpersonalized global collaborative information into sequential recommendationsystems. Specifically, we first learn an adaptive global graph among all itemsand capture global collaborative information with it in a self-supervisedfashion, whose computational burden can be further alleviated by the proposedSVD-based accelerator. Furthermore, based on the graph, we propose to extractand utilize personalized item correlations in the form of relative positionalencoding, which is a highly compatible manner of personalizing the utilizationof global collaborative information. Finally, the entire framework is optimizedin a multi-task learning paradigm, thus each part of APGL4SR can be mutuallyreinforced. As a generic framework, APGL4SR can outperform other baselines withsignificant margins. The code is available athttps://github.com/Graph-Team/APGL4SR.

APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation