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

Self-supervised learning has gradually emerged as a powerful technique forgraph representation learning. However, transferable, generalizable, and robustrepresentation learning on graph data still remains a challenge forpre-training graph neural networks. In this paper, we propose a simple andeffective self-supervised pre-training strategy, named Pairwise Half-graphDiscrimination (PHD), that explicitly pre-trains a graph neural network atgraph-level. PHD is designed as a simple binary classification task todiscriminate whether two half-graphs come from the same source. Experimentsdemonstrate that the PHD is an effective pre-training strategy that offerscomparable or superior performance on 13 graph classification tasks comparedwith state-of-the-art strategies, and achieves notable improvements whencombined with node-level strategies. Moreover, the visualization of learnedrepresentation revealed that PHD strategy indeed empowers the model to learngraph-level knowledge like the molecular scaffold. These results haveestablished PHD as a powerful and effective self-supervised learning strategyin graph-level representation learning.

Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks