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 been investigated for potentialapplicability in multiple fields that employ graph data. However, there are nostandard training settings to ensure fair comparisons among new methods,including different model architectures and data augmentation techniques. Weintroduce a standard, reproducible benchmark to which the same trainingsettings can be applied for node classification. For this benchmark, weconstructed 9 datasets, including both small- and medium-scale datasets fromdifferent fields, and 7 different models. We design a k-fold model assessmentstrategy for small datasets and a standard set of model training procedures forall datasets, enabling a standard experimental pipeline for GNNs to help ensurefair model architecture comparisons. We use node2vec and Laplacian eigenvectorsto perform data augmentation to investigate how input features affect theperformance of the models. We find topological information is important fornode classification tasks. Increasing the number of model layers does notimprove the performance except on the PATTERN and CLUSTER datasets, in whichthe graphs are not connected. Data augmentation is highly useful, especiallyusing node2vec in the baseline, resulting in a substantial baseline performanceimprovement.

A pipeline for fair comparison of graph neural networks in node classification tasks