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 Attention Networks (GATs) are the state-of-the-art neural architecturefor representation learning with graphs. GATs learn attention functions thatassign weights to nodes so that different nodes have different influences inthe feature aggregation steps. In practice, however, induced attentionfunctions are prone to over-fitting due to the increasing number of parametersand the lack of direct supervision on attention weights. GATs also suffer fromover-smoothing at the decision boundary of nodes. Here we propose a frameworkto address their weaknesses via margin-based constraints on attention duringtraining. We first theoretically demonstrate the over-smoothing behavior ofGATs and then develop an approach using constraint on the attention weightsaccording to the class boundary and feature aggregation pattern. Furthermore,to alleviate the over-fitting problem, we propose additional constraints on thegraph structure. Extensive experiments and ablation studies on common benchmarkdatasets demonstrate the effectiveness of our method, which leads tosignificant improvements over the previous state-of-the-art graph attentionmethods on all datasets.

Improving Graph Attention Networks with Large Margin-based Constraints