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

Graph convolutional neural networks (GCN) have been the model of choice forgraph representation learning, which is mainly due to the effective design ofgraph convolution that computes the representation of a node by aggregatingthose of its neighbors. However, existing GCN variants commonly use 1-D graphconvolution that solely operates on the object link graph without exploringinformative relational information among object attributes. This significantlylimits their modeling capability and may lead to inferior performance on noisyand sparse real-world networks. In this paper, we explore 2-D graph convolutionto jointly model object links and attribute relations for graph representationlearning. Specifically, we propose a computationally efficient dimensionwiseseparable 2-D graph convolution (DSGC) for filtering node features.Theoretically, we show that DSGC can reduce intra-class variance of nodefeatures on both the object dimension and the attribute dimension to learn moreeffective representations. Empirically, we demonstrate that by modelingattribute relations, DSGC achieves significant performance gain overstate-of-the-art methods for node classification and clustering on a variety ofreal-world networks. The source code for reproducing the experimental resultsis available at https://github.com/liqimai/DSGC.

Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs