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

Graph convolutional networks (GCNs) have achieved promising performance onvarious graph-based tasks. However they suffer from over-smoothing whenstacking more layers. In this paper, we present a quantitative study on thisobservation and develop novel insights towards the deeper GCN. First, weinterpret the current graph convolutional operations from an optimizationperspective and argue that over-smoothing is mainly caused by the naivefirst-order approximation of the solution to the optimization problem.Subsequently, we introduce two metrics to measure the over-smoothing onnode-level tasks. Specifically, we calculate the fraction of the pairwisedistance between connected and disconnected nodes to the overall distancerespectively. Based on our theoretical and empirical analysis, we establish auniversal theoretical framework of GCN from an optimization perspective andderive a novel convolutional kernel named GCN+ which has lower parameter amountwhile relieving the over-smoothing inherently. Extensive experiments onreal-world datasets demonstrate the superior performance of GCN+ overstate-of-the-art baseline methods on the node classification tasks.

Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective