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

Collaborative filtering-based recommender systems that rely on a single typeof behavior often encounter serious sparsity issues in real-world applications,leading to unsatisfactory performance. Multi-behavior Recommendation (MBR) is amethod that seeks to learn user preferences, represented as vector embeddings,from auxiliary information. By leveraging these preferences for target behaviorrecommendations, MBR addresses the sparsity problem and improves the accuracyof recommendations. In this paper, we propose MB-HGCN, a novel multi-behaviorrecommendation model that uses a hierarchical graph convolutional network tolearn user and item embeddings from coarse-grained on the global level tofine-grained on the behavior-specific level. Our model learns global embeddingsfrom a unified homogeneous graph constructed by the interactions of allbehaviors, which are then used as initialized embeddings for behavior-specificembedding learning in each behavior graph. We also emphasize the distinct ofthe user and item behaviorspecific embeddings and design twosimple-yet-effective strategies to aggregate the behavior-specific embeddingsfor users and items, respectively. Finally, we adopt multi-task learning foroptimization. Extensive experimental results on three real-world datasetsdemonstrate that our model significantly outperforms the baselines, achieving arelative improvement of 73.93% and 74.21% for HR@10 and NDCG@10, respectively,on the Tmall datasets.

MB-HGCN: A Hierarchical Graph Convolutional Network for Multi-behavior Recommendation