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

Convolution Neural Network (CNN) has gained tremendous success in computervision tasks with its outstanding ability to capture the local latent features.Recently, there has been an increasing interest in extending convolutionoperations to the non-Euclidean geometry. Although various types of convolutionoperations have been proposed for graphs or manifolds, their connections withtraditional convolution over grid-structured data are not well-understood. Inthis paper, we show that depthwise separable convolution can be successfullygeneralized for the unification of both graph-based and grid-based convolutionmethods. Based on this insight we propose a novel Depthwise Separable GraphConvolution (DSGC) approach which is compatible with the tradition convolutionnetwork and subsumes existing convolution methods as special cases. It isequipped with the combined strengths in model expressiveness, compatibility(relatively small number of parameters), modularity and computationalefficiency in training. Extensive experiments show the outstanding performanceof DSGC in comparison with strong baselines on multi-domain benchmark datasets.

Learning Depthwise Separable Graph Convolution from Data Manifold