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/

Zendy Plus

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

Zendy Tools

Zendy Open

Graph Convolutional Networks (GCNs) are state-of-the-art graph basedrepresentation learning models by iteratively stacking multiple layers ofconvolution aggregation operations and non-linear activation operations.Recently, in Collaborative Filtering (CF) based Recommender Systems (RS), bytreating the user-item interaction behavior as a bipartite graph, someresearchers model higher-layer collaborative signals with GCNs. These GCN basedrecommender models show superior performance compared to traditional works.However, these models suffer from training difficulty with non-linearactivations for large user-item graphs. Besides, most GCN based models couldnot model deeper layers due to the over smoothing effect with the graphconvolution operation. In this paper, we revisit GCN based CF models from twoaspects. First, we empirically show that removing non-linearities would enhancerecommendation performance, which is consistent with the theories in simplegraph convolutional networks. Second, we propose a residual network structurethat is specifically designed for CF with user-item interaction modeling, whichalleviates the over smoothing problem in graph convolution aggregationoperation with sparse user-item interaction data. The proposed model is alinear model and it is easy to train, scale to large datasets, and yield betterefficiency and effectiveness on two real datasets. We publish the source codeat https://github.com/newlei/LRGCCF.

Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach