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 neural networks (GNNs) have received much attention recently because oftheir excellent performance on graph-based tasks. However, existing research onGNNs focuses on designing more effective models without considering much aboutthe quality of the input data. In this paper, we propose self-enhanced GNN(SEG), which improves the quality of the input data using the outputs ofexisting GNN models for better performance on semi-supervised nodeclassification. As graph data consist of both topology and node labels, weimprove input data quality from both perspectives. For topology, we observethat higher classification accuracy can be achieved when the ratio ofinter-class edges (connecting nodes from different classes) is low and proposetopology update to remove inter-class edges and add intra-class edges. For nodelabels, we propose training node augmentation, which enlarges the training setusing the labels predicted by existing GNN models. SEG is a general frameworkthat can be easily combined with existing GNN models. Experimental resultsvalidate that SEG consistently improves the performance of well-known GNNmodels such as GCN, GAT and SGC across different datasets.

Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs